Leaderboard
A Maltese Evaluation Language Benchmark ๐ฒ๐น
- "headers": [
- "T",
- "Model",
- "N-Shot",
- "Version",
- "Average (All) โฌ๏ธ",
- "Average (NLU) ๐ง ",
- "Average (NLG) โ๏ธ",
- "Sentiment Analysis (F1)",
- "SIB200 (F1)",
- "Taxi1500 (F1)",
- "Maltese News Categories (F1)",
- "MultiEURLEX (F1)",
- "Belebele (Accuracy)",
- "OPUS-100 ENโMT (BLEU)",
- "OPUS-100 ENโMT (ChrF)",
- "Flores-200 ENโMT (BLEU)",
- "Flores-200 ENโMT (ChrF)",
- "WebNLG (ChrF)",
- "WebNLG (Rouge-L)",
- "EUR-Lex-Sum (ChrF)",
- "EUR-Lex-Sum (Rouge-L)",
- "Maltese News Headlines (ChrF)",
- "Maltese News Headlines (Rouge-L)",
- "Type",
- "Maltese Training",
- "#Languages",
- "Architecture",
- "Precision",
- "Hub License",
- "#Params (B)",
- "Hub โค๏ธ",
- "Available on the hub",
- "Model SHA"
- "data": [
- [
- "IT/IT",
- "<a target="_blank" href="https://huggingface.co/CohereForAI/aya-101" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">CohereForAI/aya-101</a>",
- 0,
- "1.0_english",
- 36.05,
- 47.39,
- 24.71,
- 78.13,
- 50.2,
- 29.52,
- 31.46,
- 18.48,
- 76.56,
- null,
- null,
- 19.51,
- 52.26,
- 36.04,
- 32.27,
- 8.21,
- 7.68,
- 30.58,
- 27.59,
- "instruction-tuned",
- "instruction-tuning",
- 101,
- "T5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 12.92,
- 662,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-xxl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-xxl</a>",
- 0,
- "1.0_english",
- 35.1,
- 48.41,
- 21.79,
- 78.55,
- 54.18,
- 21.67,
- 36.07,
- 18.31,
- 81.67,
- 7.77,
- 28.28,
- 3.28,
- 25.01,
- 25.68,
- 26.17,
- 3.79,
- 3.16,
- 27.35,
- 26.8,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 13.95,
- 60,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-xxl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-xxl</a>",
- 0,
- "1.0_maltese",
- 34.83,
- 46.3,
- 23.35,
- 77.63,
- 50.82,
- 13.94,
- 35.37,
- 18.16,
- 81.89,
- 12.48,
- 35.85,
- 6.09,
- 33.27,
- 17.3,
- 22.5,
- 3.31,
- 2.7,
- 27.75,
- 27.64,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 13.95,
- 60,
- true,
- "main"
- [
- "IT/IT",
- "<a target="_blank" href="https://huggingface.co/CohereForAI/aya-101" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">CohereForAI/aya-101</a>",
- 0,
- "1.0_maltese",
- 29.33,
- 33.56,
- 25.09,
- 55.26,
- 36.15,
- 4.2,
- 18.81,
- 14.25,
- 72.67,
- null,
- null,
- 19.7,
- 53.12,
- 38.12,
- 33.61,
- 5.09,
- 5.48,
- 32.81,
- 28.75,
- "instruction-tuned",
- "instruction-tuning",
- 101,
- "T5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 12.92,
- 662,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-7b-instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-7b-instruct</a>",
- 0,
- "1.0_english",
- 29.1,
- 41.56,
- 16.64,
- 73.4,
- 53.24,
- 15.07,
- 26.92,
- 11.74,
- 69,
- 9.11,
- 39.35,
- 5.52,
- 41.61,
- 2.12,
- 2.59,
- 0.2,
- 0.1,
- 0.03,
- 0.02,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 7.77,
- 72,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-xl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-xl</a>",
- 0,
- "1.0_maltese",
- 26.78,
- 42.26,
- 11.29,
- 77.82,
- 47.95,
- 14.18,
- 32.15,
- 16.24,
- 65.22,
- null,
- null,
- 0.58,
- 10.71,
- 20.09,
- 23.15,
- 3.7,
- 2.95,
- 23.84,
- 22.72,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 3.74,
- 32,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-xl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-xl</a>",
- 0,
- "1.0_english",
- 25.71,
- 40.77,
- 10.65,
- 72.33,
- 47.49,
- 9.64,
- 32.47,
- 16.82,
- 65.89,
- null,
- null,
- 0.45,
- 8.61,
- 30.29,
- 29.64,
- 4.7,
- 1.14,
- 9.71,
- 13.2,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 3.74,
- 32,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-7b-instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-7b-instruct</a>",
- 0,
- "1.0_maltese",
- 24.53,
- 31.98,
- 17.09,
- 38.85,
- 40.9,
- 10.36,
- 23.87,
- 9.54,
- 68.33,
- 4.8,
- 34.74,
- 7.89,
- 46.7,
- 3.86,
- 3.8,
- 0.19,
- 0.13,
- 0.04,
- 0.02,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 7.77,
- 72,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Meta-Llama-3-8B-Instruct</a>",
- 0,
- "1.0_english",
- 23.13,
- 30.71,
- 15.54,
- 37.17,
- 43.61,
- 16.49,
- 21.99,
- 13.18,
- 51.85,
- null,
- null,
- 8.8,
- 39.85,
- 12.59,
- 6.52,
- 1.01,
- 1.08,
- 31.68,
- 24.16,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama3",
- 8.03,
- 4315,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-9b-it" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-9b-it</a>",
- 0,
- "1.0_english",
- 23.1,
- 44.6,
- 1.6,
- 72.13,
- 60.93,
- 34.22,
- null,
- 16.43,
- 83.89,
- 0,
- 0,
- 0,
- 0,
- 8.01,
- 6.34,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 9.24,
- 748,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-large" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-large</a>",
- 0,
- "1.0_english",
- 22.11,
- 36.07,
- 8.14,
- 75.88,
- 45.8,
- 13.62,
- 29.83,
- 17.65,
- 33.67,
- null,
- null,
- 0.19,
- 6.58,
- 24.84,
- 24.46,
- 5.37,
- 2.39,
- 6.33,
- 6.9,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 1.23,
- 49,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-large" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-large</a>",
- 0,
- "1.0_maltese",
- 21.63,
- 35.14,
- 8.12,
- 76.2,
- 49.47,
- 5.04,
- 28.82,
- 16.95,
- 34.33,
- null,
- null,
- 0.5,
- 5.61,
- 21.92,
- 22.18,
- 4.88,
- 2.49,
- 8.52,
- 10.6,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 1.23,
- 49,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-9b-it" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-9b-it</a>",
- 0,
- "1.0_maltese",
- 20.82,
- 40.39,
- 1.25,
- 80.71,
- 31.18,
- 11.89,
- 21.46,
- 11.89,
- 85.22,
- 0,
- 0,
- 0,
- 0,
- 6.27,
- 4.95,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 9.24,
- 748,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-2b-instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-2b-instruct</a>",
- 0,
- "1.0_english",
- 20.37,
- 28.74,
- 12,
- 75.39,
- 20.04,
- 10.73,
- 31.03,
- 10.33,
- 24.89,
- 2.72,
- 23.41,
- 3.51,
- 34.09,
- 1.95,
- 1.83,
- 0,
- 0,
- 1.08,
- 0.56,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 2.25,
- 25,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-1.7B-Instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-1.7B-Instruct</a>",
- 0,
- "1.0_english",
- 20.12,
- 18.39,
- 21.85,
- 27.97,
- 13.99,
- 4.23,
- 26.32,
- 13.73,
- 24.11,
- 9.2,
- 37.04,
- 15.73,
- 51.08,
- 11.71,
- 5.74,
- 0,
- 0,
- 16.42,
- 9.44,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 1.66,
- 94,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-3b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-3b</a>",
- 0,
- "1.0_english",
- 19.79,
- 32.86,
- 6.73,
- 62.79,
- 42.89,
- 16.26,
- 27.53,
- 14.77,
- 32.89,
- null,
- null,
- 0.47,
- 10.31,
- 11.47,
- 10.2,
- 0.39,
- 0.46,
- 17.46,
- 11.39,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 3,
- 81,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-9B-Instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-9B-Instruct</a>",
- 0,
- "1.0_english",
- 19.63,
- 37.03,
- 2.23,
- 68.14,
- 41.24,
- 23.05,
- 12.56,
- 7.65,
- 69.56,
- 0,
- 0,
- 0,
- 0,
- 11.17,
- 4.87,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 9.15,
- 190,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-7b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-7b1</a>",
- 0,
- "1.0_english",
- 19.48,
- 32.81,
- 6.15,
- 56.39,
- 48.77,
- 21.22,
- 27.4,
- 14.22,
- 28.89,
- null,
- null,
- 0.97,
- 13.68,
- 5.34,
- 4.55,
- 0.81,
- 1.09,
- 16.78,
- 10.66,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 7.07,
- 146,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-base" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-base</a>",
- 0,
- "1.0_english",
- 19.12,
- 31.9,
- 6.34,
- 66.26,
- 43.09,
- 5.9,
- 33.82,
- 13.44,
- 28.89,
- null,
- null,
- 0.2,
- 5.33,
- 21.1,
- 21.33,
- 2.63,
- 0.38,
- 4.17,
- 4.89,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0.58,
- 32,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Meta-Llama-3-8B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Meta-Llama-3-8B</a>",
- 0,
- "1.0_english",
- 18.84,
- 26.31,
- 11.36,
- 25.97,
- 29.47,
- 15.75,
- 26.79,
- 16.22,
- 43.67,
- 3.3,
- 12.49,
- 5.34,
- 32.76,
- 11.27,
- 6,
- 0,
- 0,
- 0.81,
- 0.3,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama3",
- 8.03,
- 6400,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/openGPT-X/Teuken-7B-instruct-research-v0.4" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openGPT-X/Teuken-7B-instruct-research-v0.4</a>",
- 0,
- "1.0_english",
- 18.78,
- 19.98,
- 17.58,
- 32.1,
- 5.69,
- 15.23,
- 15.65,
- 6.17,
- 45.04,
- 0.85,
- 6.42,
- 12.04,
- 46.4,
- 9.67,
- 5.13,
- 2.53,
- 2.49,
- 31.16,
- 22.94,
- "instruction-tuned",
- "pre-training",
- 24,
- "LlamaForCausalLM",
- "?",
- "other",
- 7.45,
- 88,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Meta-Llama-3-8B-Instruct</a>",
- 0,
- "1.0_maltese",
- 18.75,
- 23.05,
- 14.46,
- 35.88,
- 24.43,
- 9.37,
- 16.26,
- 13.8,
- 38.56,
- null,
- null,
- 5.07,
- 35.97,
- 12.4,
- 4.67,
- 0.42,
- 0.35,
- 29.92,
- 23.57,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama3",
- 8.03,
- 4315,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-base" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-base</a>",
- 0,
- "1.0_maltese",
- 18.02,
- 28.95,
- 7.08,
- 56.95,
- 41.51,
- 4.2,
- 28.65,
- 13.95,
- 28.44,
- null,
- null,
- 0.79,
- 11.2,
- 13.9,
- 12.94,
- 3.48,
- 1.61,
- 6.94,
- 8.7,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0.58,
- 32,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-9b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-9b</a>",
- 0,
- "1.0_english",
- 17.52,
- 33.05,
- 1.98,
- 25.97,
- 59.16,
- 25.47,
- null,
- 13.15,
- 74.56,
- 0,
- 0,
- 0,
- 0,
- 9.82,
- 3.88,
- 0.21,
- 0.09,
- 0.01,
- 0,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 9.24,
- 680,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-7b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-7b</a>",
- 0,
- "1.0_english",
- 17.17,
- 23.79,
- 10.55,
- 26.98,
- 26.43,
- 15.44,
- 27.74,
- 10.46,
- 35.67,
- 1.99,
- 17.12,
- 7.91,
- 33.04,
- 2.4,
- 1.62,
- 0,
- 0,
- 0.26,
- 0.18,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 7.77,
- 29,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-1b7" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-1b7</a>",
- 0,
- "1.0_english",
- 17.1,
- 28.95,
- 5.25,
- 51.89,
- 41.53,
- 14.67,
- 24.01,
- 13.95,
- 27.67,
- null,
- null,
- 0.59,
- 10.99,
- 8.16,
- 5.82,
- 0.36,
- 0.4,
- 10.81,
- 6.71,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.72,
- 23,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-small" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-small</a>",
- 0,
- "1.0_english",
- 16.97,
- 26.22,
- 7.71,
- 55.48,
- 33.6,
- 4.29,
- 25.76,
- 13.81,
- 24.39,
- null,
- null,
- 2.16,
- 19.99,
- 14.32,
- 15.26,
- 3.89,
- 1.33,
- 3.29,
- 2.91,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0.3,
- 31,
- true,
- "main"
- [
- "IT/?",
- "<a target="_blank" href="https://huggingface.co/mistralai/Ministral-8B-Instruct-2410" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">mistralai/Ministral-8B-Instruct-2410</a>",
- 0,
- "1.0_english",
- 16.85,
- 26.82,
- 6.88,
- 47.41,
- 34.42,
- 6.22,
- 18.9,
- 13.42,
- 40.56,
- 1.2,
- 6.74,
- 1.25,
- 16.93,
- 10.54,
- 5.04,
- 0.17,
- 0.18,
- 0.09,
- 0.03,
- "instruction-tuned",
- "unknown",
- "?",
- "MistralForCausalLM",
- "?",
- "other",
- 8.02,
- 564,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-2b-it" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-2b-it</a>",
- 0,
- "1.0_english",
- 16.25,
- 30.17,
- 2.32,
- 26.98,
- 39.37,
- 18.15,
- 34.57,
- 14.42,
- 47.56,
- 0,
- 0,
- 0,
- 0,
- 11.6,
- 6.53,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 2.61,
- 1240,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-2b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-2b</a>",
- 0,
- "1.0_english",
- 16.06,
- 21.79,
- 10.33,
- 58.99,
- 9.77,
- 13.58,
- 18.31,
- 8.55,
- 21.56,
- 1.42,
- 17.3,
- 3.67,
- 25.71,
- 2.87,
- 2.5,
- 0,
- 0,
- 10.94,
- 5.79,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 2.25,
- 24,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/openGPT-X/Teuken-7B-instruct-research-v0.4" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openGPT-X/Teuken-7B-instruct-research-v0.4</a>",
- 0,
- "1.0_maltese",
- 15.97,
- 19.12,
- 12.82,
- 40.33,
- 7.15,
- 10.69,
- 5.65,
- 8.06,
- 42.85,
- 0.83,
- 9.42,
- 1.77,
- 19.59,
- 11.54,
- 4.86,
- 3.16,
- 3.43,
- 25.78,
- 20.11,
- "instruction-tuned",
- "pre-training",
- 24,
- "LlamaForCausalLM",
- "?",
- "other",
- 7.45,
- 88,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-9B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-9B</a>",
- 0,
- "1.0_english",
- 15.96,
- 29.77,
- 2.16,
- 58.54,
- 38.66,
- 18.14,
- 6.11,
- 5.94,
- 51.22,
- 0,
- 0,
- 0,
- 0,
- 10.81,
- 4.49,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 9.15,
- 155,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-9b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-9b</a>",
- 0,
- "1.0_maltese",
- 15.78,
- 29.44,
- 2.13,
- 26.98,
- 31.34,
- 8.67,
- 21.15,
- 15.37,
- 73.11,
- 0,
- 0,
- 0,
- 0,
- 10.13,
- 4.3,
- 0.42,
- 0.5,
- 0.04,
- 0.04,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 9.24,
- 680,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-2b-instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-2b-instruct</a>",
- 0,
- "1.0_maltese",
- 15.58,
- 20.91,
- 10.26,
- 49.25,
- 14.43,
- 4.2,
- 23.21,
- 8.78,
- 25.56,
- 2.14,
- 19.12,
- 3.17,
- 28.13,
- 3.69,
- 2.34,
- 0,
- 0,
- 0.61,
- 0.36,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 2.25,
- 25,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-1b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-1b1</a>",
- 0,
- "1.0_english",
- 15.31,
- 26,
- 4.62,
- 50.36,
- 36.03,
- 10.14,
- 23.34,
- 15.13,
- 21,
- null,
- null,
- 0.19,
- 7.69,
- 4.64,
- 3.39,
- 2.02,
- 2.88,
- 13.8,
- 7.9,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.06,
- 33,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-560m" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-560m</a>",
- 0,
- "1.0_english",
- 14.9,
- 25.66,
- 4.14,
- 49.6,
- 32.67,
- 8.69,
- 20.77,
- 14.92,
- 27.28,
- null,
- null,
- 0.24,
- 6.77,
- 7.09,
- 4.93,
- 0.75,
- 1.01,
- 11.89,
- 5.86,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 0.56,
- 131,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-7b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-7b</a>",
- 0,
- "1.0_maltese",
- 14.66,
- 19.37,
- 9.96,
- 25.97,
- 10.1,
- 12.24,
- 16.98,
- 6.46,
- 44.44,
- 1.56,
- 17.32,
- 6.29,
- 28.83,
- 3.41,
- 3.17,
- 0.06,
- 0.06,
- 0.31,
- 0.18,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 7.77,
- 29,
- true,
- "main"
- [
- "IT/?",
- "<a target="_blank" href="https://huggingface.co/mistralai/Ministral-8B-Instruct-2410" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">mistralai/Ministral-8B-Instruct-2410</a>",
- 0,
- "1.0_maltese",
- 14.31,
- 19.63,
- 8.99,
- 46.11,
- 4.05,
- 12.17,
- 12.21,
- 13.56,
- 29.67,
- 0.8,
- 4.24,
- 1.36,
- 17.39,
- 10.64,
- 4.51,
- 0.11,
- 0.07,
- 19.36,
- 12.6,
- "instruction-tuned",
- "unknown",
- "?",
- "MistralForCausalLM",
- "?",
- "other",
- 8.02,
- 564,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-small" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-small</a>",
- 0,
- "1.0_maltese",
- 13.89,
- 22.93,
- 4.84,
- 42.33,
- 34.33,
- 4.2,
- 20.26,
- 13.7,
- 22.78,
- null,
- null,
- 0.38,
- 9.39,
- 11.08,
- 10.55,
- 4.14,
- 1.72,
- 2.88,
- 2,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0.3,
- 31,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/ai-forever/mGPT-13B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">ai-forever/mGPT-13B</a>",
- 0,
- "1.0_maltese",
- 13.68,
- 20.67,
- 6.69,
- 49.12,
- 27.74,
- 4.2,
- 8.32,
- 7.18,
- 27.44,
- 0.16,
- 12.29,
- 0.33,
- 12.23,
- 8.69,
- 4.1,
- 0.05,
- 0.11,
- 0.61,
- 0.12,
- "pre-trained",
- "none",
- 61,
- "GPT2LMHeadModel",
- "?",
- "mit",
- 0,
- 49,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-7b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-7b1</a>",
- 0,
- "1.0_maltese",
- 13.65,
- 25.26,
- 2.04,
- 50.2,
- 39.29,
- 7.85,
- 18.49,
- 12.75,
- 23,
- null,
- null,
- 0.72,
- 7.75,
- 2.28,
- 1.83,
- 0,
- 0,
- 0.3,
- 0.17,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 7.07,
- 146,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-7b-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-7b-hf</a>",
- 0,
- "1.0_english",
- 13.27,
- 24.35,
- 2.19,
- 43.63,
- 25.77,
- 18.06,
- 20.97,
- 10.75,
- 26.93,
- null,
- null,
- 0,
- 0,
- 10.96,
- 4.54,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 6.74,
- 2213,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/CohereForAI/aya-23-8B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">CohereForAI/aya-23-8B</a>",
- 0,
- "1.0_english",
- 13.17,
- 22.79,
- 3.56,
- 53.09,
- 16.91,
- 10.79,
- 4.45,
- 12.21,
- 39.26,
- null,
- null,
- 0,
- 0.5,
- 11.16,
- 4.91,
- 0,
- 0,
- 11.54,
- 6.15,
- "instruction-tuned",
- "none",
- 23,
- "CohereForCausalLM",
- "?",
- "cc-by-nc-4.0",
- 8.03,
- 425,
- true,
- "main"
- [
- "IT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-7b-chat-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-7b-chat-hf</a>",
- 0,
- "1.0_english",
- 12.86,
- 23.26,
- 2.46,
- 31.79,
- 34.02,
- 11.86,
- 19.93,
- 10.34,
- 31.59,
- null,
- null,
- 0,
- 0.04,
- 12.26,
- 5.9,
- 0,
- 0,
- 0,
- 0,
- "instruction-tuned",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 6.74,
- 4670,
- true,
- "main"
- [
- "IT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-13b-chat-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-13b-chat-hf</a>",
- 0,
- "1.0_english",
- 12.85,
- 23.7,
- 2,
- 27.97,
- 30.87,
- 19.64,
- 13.06,
- 16.63,
- 34,
- null,
- null,
- 0,
- 0,
- 10,
- 6.77,
- 0,
- 0,
- 0,
- 0,
- "instruction-tuned",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 13.02,
- 1105,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-9B-Instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-9B-Instruct</a>",
- 0,
- "1.0_maltese",
- 12.82,
- 23.13,
- 2.51,
- 25.97,
- 23.79,
- 4.2,
- 11.25,
- 10.31,
- 63.22,
- 0,
- 0.04,
- 0,
- 0.59,
- 11.84,
- 6.25,
- 0,
- 0,
- 0.16,
- 0.1,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 9.15,
- 190,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Meta-Llama-3-8B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Meta-Llama-3-8B</a>",
- 0,
- "1.0_maltese",
- 12.78,
- 14.39,
- 11.17,
- 36.29,
- 24.29,
- 4.2,
- 7.29,
- 14.3,
- null,
- 1.56,
- 6.3,
- 2.88,
- 23.5,
- 10.94,
- 5.04,
- 0.15,
- 0.12,
- 20.5,
- 15.02,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama3",
- 8.03,
- 6400,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/ai-forever/mGPT-13B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">ai-forever/mGPT-13B</a>",
- 0,
- "1.0_english",
- 12.7,
- 19.22,
- 6.18,
- 38.5,
- 15.65,
- 11.98,
- 16.02,
- 7.51,
- 25.67,
- 0.28,
- 8.62,
- 0.22,
- 11,
- 9.28,
- 4.32,
- 0.06,
- 0.07,
- 4.99,
- 1.94,
- "pre-trained",
- "none",
- 61,
- "GPT2LMHeadModel",
- "?",
- "mit",
- 0,
- 49,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-564M" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-564M</a>",
- 0,
- "1.0_maltese",
- 12.52,
- 19.72,
- 5.32,
- 46.35,
- 24.35,
- 4.2,
- 5.98,
- 14.87,
- 22.56,
- null,
- null,
- 0.31,
- 12.06,
- 9.64,
- 4.24,
- 2.71,
- 3.08,
- 7.48,
- 1.83,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 53,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-1.7B-Instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-1.7B-Instruct</a>",
- 0,
- "1.0_maltese",
- 12.32,
- 14.88,
- 9.76,
- 25.97,
- 3.12,
- 4.2,
- 18.58,
- 11.98,
- 25.44,
- 0,
- 2.61,
- 10.45,
- 35.23,
- 10.75,
- 5.23,
- 0,
- 0,
- 0.4,
- 0.19,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 1.66,
- 94,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-7b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-7b1</a>",
- 0,
- "1.0_english",
- 12.21,
- 22.24,
- 2.17,
- 25.97,
- 36.63,
- 13.88,
- 20.04,
- 12.84,
- 24.11,
- null,
- null,
- 0,
- 0.22,
- 10.63,
- 5.32,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 7.07,
- 203,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-7.5B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-7.5B</a>",
- 0,
- "1.0_maltese",
- 12.01,
- 19.1,
- 4.92,
- 55.16,
- 12.16,
- 4.23,
- 6.7,
- 13.46,
- 22.89,
- null,
- null,
- 1.28,
- 11.4,
- 10.21,
- 4.3,
- 0.84,
- 1.16,
- 5.84,
- 1.82,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 59,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-2.9B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-2.9B</a>",
- 0,
- "1.0_maltese",
- 11.87,
- 17.64,
- 6.1,
- 48.6,
- 8.7,
- 4.2,
- 6.45,
- 14.74,
- 23.17,
- null,
- null,
- 1.21,
- 16.24,
- 10.22,
- 4.34,
- 1.4,
- 1.85,
- 6.26,
- 2.2,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 10,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-2b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-2b</a>",
- 0,
- "1.0_maltese",
- 11.86,
- 14.81,
- 8.92,
- 39.15,
- 7.06,
- 4.2,
- 7.98,
- 6.44,
- 24,
- 0.49,
- 10.97,
- 3.51,
- 22.43,
- 6.93,
- 4.86,
- 0,
- 0,
- 7.67,
- 4.25,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 2.25,
- 24,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-1b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-1b1</a>",
- 0,
- "1.0_english",
- 11.76,
- 21.42,
- 2.1,
- 56.14,
- 15.85,
- 9.98,
- 10.69,
- 13.66,
- 22.19,
- null,
- null,
- 0,
- 0.06,
- 10.45,
- 5.37,
- 0,
- 0,
- 0.02,
- 0,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.06,
- 64,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-1.7B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-1.7B</a>",
- 0,
- "1.0_maltese",
- 11.71,
- 17.04,
- 6.38,
- 42.07,
- 14.23,
- 4.2,
- 6.48,
- 12.47,
- 22.78,
- null,
- null,
- 1.43,
- 16.95,
- 10.24,
- 4.51,
- 2.35,
- 2.59,
- 7.47,
- 2.12,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 20,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-3b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-3b</a>",
- 0,
- "1.0_maltese",
- 11.46,
- 22.32,
- 0.61,
- 39.36,
- 26.37,
- 6.31,
- 20.73,
- 15.12,
- 26,
- null,
- null,
- 0,
- 0.19,
- 2.77,
- 2.2,
- 0,
- 0,
- 0.12,
- 0.07,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 3,
- 81,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-3b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-3b</a>",
- 0,
- "1.0_english",
- 11.37,
- 20.61,
- 2.13,
- 32.86,
- 30.61,
- 5.4,
- 15.63,
- 14.34,
- 24.83,
- null,
- null,
- 0,
- 0.26,
- 10.36,
- 5.37,
- 0,
- 0,
- 0.01,
- 0.01,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 3,
- 93,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-4.5B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-4.5B</a>",
- 0,
- "1.0_maltese",
- 11.26,
- 16.3,
- 6.23,
- 32.95,
- 13.28,
- 4.27,
- 8.97,
- 14.43,
- 23.89,
- null,
- null,
- 1.87,
- 18.76,
- 10.57,
- 4.65,
- 0.45,
- 0.42,
- 4.09,
- 1.39,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 5.08,
- 20,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-9B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-9B</a>",
- 0,
- "1.0_maltese",
- 11.26,
- 20.03,
- 2.49,
- 25.97,
- 22.61,
- 4.2,
- 3.75,
- 11.43,
- 52.22,
- 0,
- 0,
- 0,
- 0.78,
- 11.66,
- 6.48,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 9.15,
- 155,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-1b7" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-1b7</a>",
- 0,
- "1.0_maltese",
- 11.19,
- 21.64,
- 0.74,
- 39.36,
- 30.3,
- 7.07,
- 16.2,
- 15.36,
- 21.56,
- null,
- null,
- 0,
- 0.04,
- 3.58,
- 2.44,
- 0,
- 0,
- 0.09,
- 0.07,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.72,
- 23,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-1.7B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-1.7B</a>",
- 0,
- "1.0_english",
- 10.81,
- 19.57,
- 2.04,
- 40.87,
- 16.58,
- 5.46,
- 18.89,
- 12.66,
- 22.94,
- null,
- null,
- 0,
- 0.04,
- 10.13,
- 4.93,
- 0.04,
- 0.03,
- 0,
- 0,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 20,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-1b7" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-1b7</a>",
- 0,
- "1.0_english",
- 10.71,
- 19.22,
- 2.21,
- 50.14,
- 5.32,
- 9.05,
- 11.66,
- 12.77,
- 26.37,
- null,
- null,
- 0,
- 0,
- 10.94,
- 5.83,
- 0,
- 0,
- 0.17,
- 0.09,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.72,
- 122,
- true,
- "main"
- [
- "IT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-7b-chat-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-7b-chat-hf</a>",
- 0,
- "1.0_maltese",
- 10.59,
- 17.37,
- 3.82,
- 42.32,
- 2.79,
- 3.73,
- 15.8,
- 11.77,
- 27.78,
- null,
- null,
- 0,
- 1.93,
- 12.59,
- 5.82,
- 0,
- 0,
- 9.55,
- 4.57,
- "instruction-tuned",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 6.74,
- 4670,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-1.7B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-1.7B</a>",
- 0,
- "1.0_english",
- 10.48,
- 18.78,
- 2.18,
- 28.6,
- 27.52,
- 4.2,
- 17.36,
- 11.87,
- 23.11,
- 0,
- 0,
- 0,
- 0,
- 10.9,
- 5.5,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 0,
- 104,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-2b-it" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-2b-it</a>",
- 0,
- "1.0_maltese",
- 10.44,
- 18.57,
- 2.31,
- 25.97,
- 4.68,
- 11.27,
- 16.17,
- 9.99,
- 43.33,
- 0,
- 0,
- 0,
- 0,
- 11.55,
- 6.15,
- 0,
- 0,
- 0.04,
- 0.02,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 2.61,
- 1240,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/MBZUAI/bactrian-x-bloom-7b1-lora" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MBZUAI/bactrian-x-bloom-7b1-lora</a>",
- 0,
- "1.0_maltese",
- 10.44,
- 18.13,
- 2.74,
- 48.1,
- 14.9,
- 4.2,
- 7.52,
- 9.95,
- 24.11,
- null,
- null,
- 0.01,
- 1.12,
- 7.98,
- 2.59,
- 0,
- 0,
- 9.81,
- 4.59,
- "instruction-tuned",
- "none",
- 77,
- "BloomForCausalLM",
- "?",
- "mit",
- 0,
- "?",
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-2.9B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-2.9B</a>",
- 0,
- "1.0_english",
- 10.34,
- 18.35,
- 2.33,
- 32.68,
- 8.94,
- 9.72,
- 21.01,
- 14.35,
- 23.41,
- null,
- null,
- 0,
- 0.93,
- 10.62,
- 4.92,
- 0,
- 0,
- 0.39,
- 0.1,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 10,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-13b-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-13b-hf</a>",
- 0,
- "1.0_english",
- 10.28,
- 18.3,
- 2.26,
- 32.86,
- 5.18,
- 8.67,
- 14.97,
- 16.37,
- 31.78,
- null,
- null,
- 0,
- 0,
- 11.29,
- 4.74,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 13.02,
- 618,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-xxl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-xxl</a>",
- 0,
- "1.0_maltese",
- 10.27,
- 15.45,
- 5.1,
- 25.97,
- 15.16,
- 4.87,
- 4.16,
- 14.3,
- 28.22,
- null,
- null,
- 0.08,
- 9.87,
- 8.64,
- 2.99,
- 4.24,
- 4.44,
- 7.27,
- 2.53,
- "pre-trained",
- "pre-training",
- 101,
- "T5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 70,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-560m" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-560m</a>",
- 0,
- "1.0_maltese",
- 10.23,
- 19.86,
- 0.6,
- 48.25,
- 17.81,
- 3.73,
- 10.64,
- 15.07,
- 23.67,
- null,
- null,
- 0,
- 0.73,
- 1.96,
- 1.35,
- 0,
- 0,
- 0.66,
- 0.31,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 0.56,
- 131,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/ai-forever/mGPT" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">ai-forever/mGPT</a>",
- 0,
- "1.0_english",
- 10.22,
- 16.38,
- 4.06,
- 32.99,
- 10.14,
- 12.53,
- 12.04,
- 7.9,
- 22.67,
- null,
- null,
- 0.27,
- 11.9,
- 7.74,
- 3.03,
- 0.16,
- 0.55,
- 0.42,
- 0.13,
- "pre-trained",
- "none",
- 61,
- "GPT2LMHeadModel",
- "?",
- "apache-2.0",
- 0,
- 270,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-xxl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-xxl</a>",
- 0,
- "1.0_english",
- 10.18,
- 15.46,
- 4.9,
- 25.97,
- 14.59,
- 4.87,
- 4.05,
- 13.96,
- 29.33,
- null,
- null,
- 0.11,
- 9.42,
- 8.41,
- 3.05,
- 4.28,
- 4.34,
- 6.79,
- 2.34,
- "pre-trained",
- "pre-training",
- 101,
- "T5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 70,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-4.5B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-4.5B</a>",
- 0,
- "1.0_english",
- 10.17,
- 18.21,
- 2.14,
- 26.65,
- 5.83,
- 11.69,
- 22.11,
- 18.24,
- 24.72,
- null,
- null,
- 0,
- 0.05,
- 10.61,
- 4.84,
- 0,
- 0,
- 0.06,
- 0.03,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 5.08,
- 20,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-2b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-2b</a>",
- 0,
- "1.0_maltese",
- 10.13,
- 18.08,
- 2.19,
- 25.97,
- 21.84,
- 7.33,
- 9.14,
- 14.11,
- 30.11,
- 0,
- 0.06,
- 0,
- 0.01,
- 10.18,
- 4.66,
- 0.24,
- 0.35,
- 0.79,
- 0.33,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 2.61,
- 610,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/DAMO-NLP-MT/polylm-1.7b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">DAMO-NLP-MT/polylm-1.7b</a>",
- 0,
- "1.0_english",
- 10.11,
- 17.03,
- 3.18,
- 46.29,
- 3.45,
- 11.97,
- 5.38,
- 12.08,
- 23,
- null,
- null,
- 0.1,
- 7.74,
- 8.19,
- 3.74,
- 0,
- 0,
- 0.01,
- 0,
- "pre-trained",
- "none",
- 18,
- "GPT2LMHeadModel",
- "?",
- "apache-2.0",
- 0,
- 11,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/DAMO-NLP-MT/polylm-13b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">DAMO-NLP-MT/polylm-13b</a>",
- 0,
- "1.0_maltese",
- 10.06,
- 17.76,
- 2.36,
- 50.43,
- 5.8,
- 9.36,
- 6.18,
- 11.71,
- 23.11,
- null,
- null,
- 0,
- 0.72,
- 11.07,
- 5.63,
- 0,
- 0,
- 0.18,
- 0.03,
- "pre-trained",
- "none",
- 18,
- "PolyLMHeadModel",
- "?",
- "apache-2.0",
- 0,
- 53,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-2b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-2b</a>",
- 0,
- "1.0_english",
- 9.96,
- 17.85,
- 2.06,
- 25.97,
- 27.04,
- 11.24,
- null,
- 10.2,
- 32.67,
- 0,
- 0.04,
- 0,
- 0.02,
- 10.01,
- 4.26,
- 0.17,
- 0.21,
- 0.01,
- 0,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 2.61,
- 610,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-1b7" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-1b7</a>",
- 0,
- "1.0_maltese",
- 9.91,
- 15.56,
- 4.26,
- 39.36,
- 6.13,
- 4.2,
- 5.11,
- 14.2,
- 24.33,
- null,
- null,
- 0.38,
- 11.51,
- 9.63,
- 4.62,
- 0,
- 0,
- 0.81,
- 0.16,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.72,
- 122,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-560m" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-560m</a>",
- 0,
- "1.0_maltese",
- 9.86,
- 16.27,
- 3.45,
- 45.2,
- 5.62,
- 4.52,
- 2.99,
- 16.69,
- 22.61,
- null,
- null,
- 0.22,
- 9.01,
- 7.97,
- 3.56,
- 0,
- 0,
- 1.49,
- 0.26,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 0.56,
- 369,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-1b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-1b1</a>",
- 0,
- "1.0_maltese",
- 9.85,
- 18.4,
- 1.3,
- 39.36,
- 14.44,
- 4.2,
- 16.68,
- 14,
- 21.72,
- null,
- null,
- 0.31,
- 2.48,
- 3.15,
- 2.31,
- 0,
- 0,
- 2.55,
- 0.87,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.06,
- 33,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-3b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-3b</a>",
- 0,
- "1.0_maltese",
- 9.77,
- 17.24,
- 2.3,
- 39.36,
- 19,
- 4.2,
- 3.74,
- 14.62,
- 22.5,
- null,
- null,
- 0.04,
- 1.6,
- 9.75,
- 4.64,
- 0,
- 0,
- 0.79,
- 0.14,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 3,
- 93,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/MBZUAI/bactrian-x-bloom-7b1-lora" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MBZUAI/bactrian-x-bloom-7b1-lora</a>",
- 0,
- "1.0_english",
- 9.67,
- 16.81,
- 2.53,
- 25.97,
- 14.83,
- 12.34,
- 15.21,
- 10.84,
- 21.67,
- null,
- null,
- 0,
- 0.17,
- 10.36,
- 5.12,
- 0,
- 0,
- 5.87,
- 2.13,
- "instruction-tuned",
- "none",
- 77,
- "BloomForCausalLM",
- "?",
- "mit",
- 0,
- "?",
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/MBZUAI/bactrian-x-llama-13b-lora" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MBZUAI/bactrian-x-llama-13b-lora</a>",
- 0,
- "1.0_maltese",
- 9.67,
- 16.11,
- 3.22,
- 45.66,
- 2.79,
- 8.93,
- 5.46,
- 10.53,
- 23.28,
- null,
- null,
- 0.63,
- 6.1,
- 8.01,
- 4.06,
- 0.19,
- 0.24,
- 4.83,
- 1.78,
- "instruction-tuned",
- "none",
- 52,
- "LlamaForCausalLM",
- "?",
- "mit",
- 0,
- 3,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-7.5B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-7.5B</a>",
- 0,
- "1.0_english",
- 9.66,
- 17.26,
- 2.07,
- 29.92,
- 10.19,
- 6.36,
- 19.31,
- 14.89,
- 22.89,
- null,
- null,
- 0,
- 0.01,
- 10.23,
- 4.78,
- 0,
- 0,
- 0.22,
- 0.11,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 59,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/ai-forever/mGPT" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">ai-forever/mGPT</a>",
- 0,
- "1.0_maltese",
- 9.53,
- 15.18,
- 3.88,
- 42.6,
- 8.59,
- 4.2,
- 5.54,
- 7.73,
- 22.44,
- null,
- null,
- 0.5,
- 12.05,
- 6.84,
- 2.96,
- 0.15,
- 0.27,
- 0.7,
- 0.24,
- "pre-trained",
- "none",
- 61,
- "GPT2LMHeadModel",
- "?",
- "apache-2.0",
- 0,
- 270,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/CohereForAI/aya-23-8B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">CohereForAI/aya-23-8B</a>",
- 0,
- "1.0_maltese",
- 9.51,
- 16.01,
- 3.02,
- 45.74,
- 4.78,
- 4.2,
- 7.37,
- 9.86,
- 24.11,
- null,
- null,
- 0.13,
- 4.04,
- 10.87,
- 5.01,
- 0.01,
- 0.01,
- 0.41,
- 0.17,
- "instruction-tuned",
- "none",
- 23,
- "CohereForCausalLM",
- "?",
- "cc-by-nc-4.0",
- 8.03,
- 425,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-1b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-1b1</a>",
- 0,
- "1.0_maltese",
- 9.42,
- 15.67,
- 3.18,
- 39.15,
- 9.53,
- 4.2,
- 3.59,
- 15.19,
- 22.33,
- null,
- null,
- 0.15,
- 6.65,
- 9.09,
- 4.07,
- 0,
- 0,
- 0.63,
- 0.14,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.06,
- 64,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-7b-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-7b-hf</a>",
- 0,
- "1.0_maltese",
- 9.35,
- 15.9,
- 2.8,
- 49.25,
- 2.78,
- 3.79,
- 7.73,
- 7.46,
- 24.39,
- null,
- null,
- 0,
- 1.17,
- 11.2,
- 4.8,
- 0,
- 0,
- 6.35,
- 1.65,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 6.74,
- 2213,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-560m" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-560m</a>",
- 0,
- "1.0_english",
- 9.29,
- 15.97,
- 2.6,
- 26.65,
- 11.08,
- 9.6,
- 8.93,
- 16.44,
- 23.15,
- null,
- null,
- 0.28,
- 3.86,
- 9.14,
- 4.56,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 0.56,
- 369,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-564M" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-564M</a>",
- 0,
- "1.0_english",
- 9.24,
- 16.57,
- 1.91,
- 29.44,
- 17.15,
- 7.52,
- 7.09,
- 15.14,
- 23.11,
- null,
- null,
- 0,
- 0,
- 9.54,
- 4.29,
- 0.02,
- 0.01,
- 0.01,
- 0.01,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 53,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-large" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-large</a>",
- 0,
- "1.0_english",
- 9.2,
- 12.64,
- 5.76,
- 28.25,
- 6.68,
- 4.87,
- 2.11,
- 11.01,
- 22.89,
- null,
- null,
- 0.08,
- 9.93,
- 11.07,
- 4.33,
- 3.18,
- 4.4,
- 8.79,
- 3.42,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 101,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/DAMO-NLP-MT/polylm-1.7b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">DAMO-NLP-MT/polylm-1.7b</a>",
- 0,
- "1.0_maltese",
- 9.15,
- 15.12,
- 3.18,
- 39.36,
- 11.44,
- 3.73,
- 3.82,
- 9.5,
- 22.89,
- null,
- null,
- 0.1,
- 8.18,
- 7.5,
- 3.31,
- 0,
- 0,
- 1.6,
- 0.21,
- "pre-trained",
- "none",
- 18,
- "GPT2LMHeadModel",
- "?",
- "apache-2.0",
- 0,
- 11,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/MaLA-LM/mala-500-10b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MaLA-LM/mala-500-10b</a>",
- 0,
- "1.0_english",
- 9.08,
- 14.76,
- 3.39,
- 25.97,
- 21.37,
- 7.45,
- 2.27,
- 3.6,
- 27.89,
- null,
- null,
- 0,
- 7.28,
- 9.68,
- 3.75,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "pre-training",
- 511,
- "LlamaForCausalLM",
- "?",
- "llama2",
- 0,
- 6,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/DAMO-NLP-MT/polylm-13b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">DAMO-NLP-MT/polylm-13b</a>",
- 0,
- "1.0_english",
- 9.04,
- 15.06,
- 3.03,
- 25.97,
- 3.84,
- 5.47,
- 20.35,
- 12.54,
- 22.17,
- null,
- null,
- 0.14,
- 3.67,
- 11.49,
- 6.03,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "none",
- 18,
- "PolyLMHeadModel",
- "?",
- "apache-2.0",
- 0,
- 53,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/MaLA-LM/mala-500-10b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MaLA-LM/mala-500-10b</a>",
- 0,
- "1.0_maltese",
- 9.04,
- 13.46,
- 4.62,
- 25.97,
- 15.78,
- 4.2,
- 1.49,
- 5.45,
- 27.89,
- null,
- null,
- 0.01,
- 12.06,
- 9.81,
- 4.54,
- 0,
- 0,
- 3.65,
- 1.2,
- "pre-trained",
- "pre-training",
- 511,
- "LlamaForCausalLM",
- "?",
- "llama2",
- 0,
- 6,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-7b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-7b1</a>",
- 0,
- "1.0_maltese",
- 8.97,
- 15.97,
- 1.96,
- 32.95,
- 15.26,
- 4.2,
- 7.45,
- 13.74,
- 22.22,
- null,
- null,
- 0,
- 0.11,
- 9.61,
- 4.41,
- 0,
- 0,
- 0.24,
- 0.1,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 7.07,
- 203,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/MBZUAI/bactrian-x-llama-13b-lora" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MBZUAI/bactrian-x-llama-13b-lora</a>",
- 0,
- "1.0_english",
- 8.89,
- 15.44,
- 2.33,
- 36.75,
- 9.09,
- 5.73,
- 7.03,
- 11.29,
- 22.78,
- null,
- null,
- 0,
- 0.59,
- 10.86,
- 5.54,
- 0.07,
- 0.07,
- 0.83,
- 0.15,
- "instruction-tuned",
- "none",
- 52,
- "LlamaForCausalLM",
- "?",
- "mit",
- 0,
- 3,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-large" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-large</a>",
- 0,
- "1.0_maltese",
- 8.79,
- 11.52,
- 6.05,
- 25.97,
- 2.43,
- 4.87,
- 2.12,
- 10.85,
- 22.89,
- null,
- null,
- 0.09,
- 11.02,
- 11.45,
- 4.86,
- 3.11,
- 4.39,
- 8.81,
- 3.39,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 101,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-1.7B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-1.7B</a>",
- 0,
- "1.0_maltese",
- 8.77,
- 13.51,
- 4.03,
- 26.98,
- 3.12,
- 4.2,
- 13.72,
- 10.17,
- 22.89,
- 0,
- 0.15,
- 1.12,
- 9.31,
- 10.67,
- 5.23,
- 0,
- 0,
- 0,
- 0,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 0,
- 104,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-13b-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-13b-hf</a>",
- 0,
- "1.0_maltese",
- 8.63,
- 14.1,
- 3.17,
- 25.97,
- 11.12,
- 4.2,
- 9.61,
- 9.7,
- 24,
- null,
- null,
- 0,
- 0.5,
- 11.6,
- 5.06,
- 0,
- 0,
- 9.21,
- 3.74,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 13.02,
- 618,
- true,
- "main"
- [
- "IT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-13b-chat-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-13b-chat-hf</a>",
- 0,
- "1.0_maltese",
- 8.26,
- 13.41,
- 3.1,
- 25.97,
- 4.59,
- 4.2,
- 10.32,
- 12.03,
- 23.33,
- null,
- null,
- 0,
- 0.01,
- 11.86,
- 6.67,
- 0,
- 0,
- 6.1,
- 3.65,
- "instruction-tuned",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 13.02,
- 1105,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-base" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-base</a>",
- 0,
- "1.0_english",
- 8.17,
- 12.9,
- 3.44,
- 31.58,
- 2.78,
- 4.95,
- 2.89,
- 7.29,
- 27.89,
- null,
- null,
- 0.04,
- 4.15,
- 4.76,
- 2.93,
- 0.33,
- 0.86,
- 8.71,
- 7.43,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 253,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-xl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-xl</a>",
- 0,
- "1.0_english",
- 7.97,
- 11.48,
- 4.46,
- 26.98,
- 4.31,
- 3.73,
- 2.08,
- 9.88,
- 21.89,
- null,
- null,
- 0.04,
- 9.01,
- 6.26,
- 2.4,
- 4.29,
- 4.46,
- 7.39,
- 2.58,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 25,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-xl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-xl</a>",
- 0,
- "1.0_maltese",
- 7.95,
- 11.12,
- 4.77,
- 25.97,
- 2.78,
- 3.73,
- 2.19,
- 10.17,
- 21.89,
- null,
- null,
- 0.03,
- 7.95,
- 9.39,
- 4.14,
- 4.19,
- 4.34,
- 6.63,
- 2.19,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 25,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-base" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-base</a>",
- 0,
- "1.0_maltese",
- 7.66,
- 12.1,
- 3.22,
- 26.98,
- 2.78,
- 4.87,
- 2.98,
- 7.13,
- 27.89,
- null,
- null,
- 0.05,
- 4.43,
- 3.57,
- 2.22,
- 0.31,
- 0.82,
- 8.55,
- 7.3,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 253,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/MBZUAI/bactrian-x-llama-7b-lora" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MBZUAI/bactrian-x-llama-7b-lora</a>",
- 0,
- "1.0_english",
- 7.62,
- 14.22,
- 1.02,
- 25.97,
- 7.97,
- 11.26,
- 6.93,
- 7.43,
- 25.74,
- null,
- null,
- 0.01,
- 2.38,
- 2.64,
- 0.8,
- 1.2,
- 0.01,
- 1.36,
- 0.09,
- "instruction-tuned",
- "none",
- 52,
- "LlamaForCausalLM",
- "?",
- "mit",
- 0,
- 4,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/MBZUAI/bactrian-x-llama-7b-lora" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MBZUAI/bactrian-x-llama-7b-lora</a>",
- 0,
- "1.0_maltese",
- 7.47,
- 14.25,
- 0.69,
- 25.65,
- 6.21,
- 12.11,
- 6.28,
- 7.54,
- 27.72,
- null,
- null,
- 0.01,
- 1.87,
- 1.45,
- 0.81,
- 1.17,
- 0.03,
- 1.22,
- 0.1,
- "instruction-tuned",
- "none",
- 52,
- "LlamaForCausalLM",
- "?",
- "mit",
- 0,
- 4,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-small" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-small</a>",
- 0,
- "1.0_english",
- 6.74,
- 11.5,
- 1.98,
- 25.97,
- 2.43,
- 3.73,
- 6.23,
- 8.72,
- 21.89,
- 0.12,
- 1.53,
- 0,
- 1.48,
- 1.43,
- 0.64,
- 0.21,
- 0.52,
- 6.29,
- 4.92,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 173,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-small" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-small</a>",
- 0,
- "1.0_maltese",
- 6.68,
- 11.48,
- 1.88,
- 25.97,
- 2.43,
- 3.73,
- 6.09,
- 8.77,
- 21.89,
- 0.01,
- 1.31,
- 0.01,
- 1.47,
- 1.43,
- 0.64,
- 0.2,
- 0.5,
- 6.06,
- 4.68,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 173,
- true,
- "main"
- [
- "metadata": null
- "headers": [
- "T",
- "Model",
- "N-Shot",
- "Version",
- "Average (All) โฌ๏ธ",
- "Average (NLU) ๐ง ",
- "Average (NLG) โ๏ธ",
- "Sentiment Analysis (F1)",
- "SIB200 (F1)",
- "Taxi1500 (F1)",
- "Maltese News Categories (F1)",
- "MultiEURLEX (F1)",
- "OPUS-100 ENโMT (BLEU)",
- "OPUS-100 ENโMT (ChrF)",
- "Flores-200 ENโMT (BLEU)",
- "Flores-200 ENโMT (ChrF)",
- "WebNLG (ChrF)",
- "WebNLG (Rouge-L)",
- "EUR-Lex-Sum (ChrF)",
- "EUR-Lex-Sum (Rouge-L)",
- "Maltese News Headlines (ChrF)",
- "Maltese News Headlines (Rouge-L)",
- "Type",
- "Maltese Training",
- "#Languages",
- "Architecture",
- "Precision",
- "Hub License",
- "#Params (B)",
- "Hub โค๏ธ",
- "Available on the hub",
- "Model SHA"
- "data": [
- [
- "IT/IT",
- "<a target="_blank" href="https://huggingface.co/CohereForAI/aya-101" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">CohereForAI/aya-101</a>",
- 1,
- "1.0_english",
- 38.61,
- 39.43,
- 37.79,
- 86.47,
- 52.33,
- 19.68,
- 23.52,
- 15.14,
- 26.84,
- 57.77,
- 21.19,
- 54.33,
- 41.21,
- 36.36,
- 8.21,
- 7.68,
- 29.95,
- 27.95,
- "instruction-tuned",
- "instruction-tuning",
- 101,
- "T5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 12.92,
- 662,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-9B-Instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-9B-Instruct</a>",
- 1,
- "1.0_maltese",
- 36.91,
- 37.43,
- 36.39,
- 79.2,
- 74.53,
- 16.62,
- 8.93,
- 7.89,
- 31.58,
- 57.51,
- 37.98,
- 68.29,
- 27.78,
- 29.05,
- 0,
- 0,
- 35.2,
- 28.36,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 9.15,
- 190,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-9b-it" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-9b-it</a>",
- 1,
- "1.0_english",
- 36.08,
- 44.36,
- 27.79,
- 84.96,
- 74.28,
- 31.91,
- 22.6,
- 8.06,
- 14.37,
- 36.72,
- 18.35,
- 52.4,
- 22.8,
- 23.35,
- 0,
- 0,
- 32.27,
- 27.04,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 9.24,
- 748,
- true,
- "main"
- [
- "IT/IT",
- "<a target="_blank" href="https://huggingface.co/CohereForAI/aya-101" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">CohereForAI/aya-101</a>",
- 1,
- "1.0_maltese",
- 35.82,
- 33.82,
- 37.82,
- 83.55,
- 45.49,
- 13.88,
- 12.86,
- 13.32,
- 27.43,
- 57.7,
- 20.89,
- 54.13,
- 43.27,
- 37.1,
- 5.09,
- 5.49,
- 30.65,
- 28.52,
- "instruction-tuned",
- "instruction-tuning",
- 101,
- "T5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 12.92,
- 662,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-9B-Instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-9B-Instruct</a>",
- 1,
- "1.0_english",
- 35.26,
- 35.61,
- 34.91,
- 78.87,
- 64.74,
- 11.73,
- 14.75,
- 7.98,
- 33.55,
- 60.38,
- 38.56,
- 68.73,
- 17.47,
- 18.14,
- 0,
- 0,
- 35.23,
- 27.97,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 9.15,
- 190,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-9b-it" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-9b-it</a>",
- 1,
- "1.0_maltese",
- 32.88,
- 40.19,
- 25.57,
- 85.57,
- 74.8,
- 20.85,
- 12.61,
- 7.14,
- 8.45,
- 26.99,
- 18.18,
- 51.76,
- 20.42,
- 20.25,
- 0,
- 0,
- 34.28,
- 28.68,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 9.24,
- 748,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/openGPT-X/Teuken-7B-instruct-research-v0.4" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openGPT-X/Teuken-7B-instruct-research-v0.4</a>",
- 1,
- "1.0_english",
- 32.12,
- 36.1,
- 28.15,
- 76.43,
- 56.93,
- 22.82,
- 17.46,
- 6.84,
- 18.81,
- 45.8,
- 18.79,
- 54.75,
- 13.61,
- 14.12,
- 2.52,
- 2.44,
- 30.97,
- 24.12,
- "instruction-tuned",
- "pre-training",
- 24,
- "LlamaForCausalLM",
- "?",
- "other",
- 7.45,
- 88,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Meta-Llama-3-8B-Instruct</a>",
- 1,
- "1.0_english",
- 31.95,
- 34.65,
- 29.25,
- 79.86,
- 56.66,
- 8.33,
- 18.75,
- 9.62,
- 17.63,
- 44.68,
- 10.86,
- 43.69,
- 30.25,
- 26.38,
- 1,
- 1.09,
- 33.59,
- 26.57,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama3",
- 8.03,
- 4315,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-7b-instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-7b-instruct</a>",
- 1,
- "1.0_maltese",
- 31.85,
- 39.31,
- 24.39,
- 79.9,
- 62.29,
- 14,
- 26.74,
- 13.61,
- 6.4,
- 39.19,
- 4.81,
- 39.03,
- 21.4,
- 17.37,
- 0.19,
- 0.15,
- 27.58,
- 22.18,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 7.77,
- 72,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/openGPT-X/Teuken-7B-instruct-research-v0.4" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">openGPT-X/Teuken-7B-instruct-research-v0.4</a>",
- 1,
- "1.0_maltese",
- 31.65,
- 33.42,
- 29.88,
- 69.41,
- 62.58,
- 15.63,
- 7.91,
- 11.57,
- 18.87,
- 45.62,
- 19.01,
- 54.94,
- 20.41,
- 17.14,
- 3.01,
- 3.28,
- 32.05,
- 25.15,
- "instruction-tuned",
- "pre-training",
- 24,
- "LlamaForCausalLM",
- "?",
- "other",
- 7.45,
- 88,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-9B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-9B</a>",
- 1,
- "1.0_maltese",
- 31.45,
- 33.13,
- 29.77,
- 81.02,
- 60.28,
- 6.13,
- 10.13,
- 8.11,
- 30.57,
- 54.63,
- 36.19,
- 67.02,
- 16.96,
- 18.19,
- 0,
- 0,
- 15.42,
- 10.26,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 9.15,
- 155,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Meta-Llama-3-8B-Instruct</a>",
- 1,
- "1.0_maltese",
- 30.74,
- 34.28,
- 27.21,
- 77.89,
- 58.26,
- 6.33,
- 18.82,
- 10.09,
- 14.54,
- 39.93,
- 10.91,
- 43.73,
- 24.57,
- 22.98,
- 0.41,
- 0.35,
- 34.98,
- 27.46,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama3",
- 8.03,
- 4315,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-7b-instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-7b-instruct</a>",
- 1,
- "1.0_english",
- 30.3,
- 36.63,
- 23.96,
- 65.12,
- 64.17,
- 17.36,
- 24.49,
- 12.01,
- 8.46,
- 43.36,
- 6.24,
- 44.28,
- 13.2,
- 10.32,
- 0.2,
- 0.1,
- 25.74,
- 18.88,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 7.77,
- 72,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-9B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-9B</a>",
- 1,
- "1.0_english",
- 30.14,
- 34.64,
- 25.64,
- 77.41,
- 65.14,
- 11.73,
- 8.77,
- 10.14,
- 23.63,
- 47.12,
- 33.97,
- 63.68,
- 14.35,
- 14.17,
- 0,
- 0,
- 4.42,
- 3.03,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 9.15,
- 155,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Meta-Llama-3-8B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Meta-Llama-3-8B</a>",
- 1,
- "1.0_english",
- 28.93,
- 33.06,
- 24.8,
- 80.59,
- 42.11,
- 6.33,
- 22.98,
- 13.31,
- 14.86,
- 39.7,
- 10.09,
- 41.76,
- 17.41,
- 17.84,
- 0,
- 0,
- 32.99,
- 25.14,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama3",
- 8.03,
- 6400,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-7b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-7b</a>",
- 1,
- "1.0_english",
- 27.68,
- 34.46,
- 20.91,
- 79.33,
- 48.07,
- 8.27,
- 25.87,
- 10.77,
- 6.91,
- 29.03,
- 12.58,
- 42.65,
- 14.9,
- 13.66,
- 0,
- 0,
- 22.79,
- 17.95,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 7.77,
- 29,
- true,
- "main"
- [
- "IT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-13b-chat-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-13b-chat-hf</a>",
- 1,
- "1.0_english",
- 27.36,
- 36.86,
- 17.86,
- 72.19,
- 62.65,
- 16.9,
- 16.52,
- 16.04,
- 7.84,
- 25.7,
- 3.93,
- 27.61,
- 15.2,
- 15.55,
- 0,
- 0,
- 29.36,
- 20.8,
- "instruction-tuned",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 13.02,
- 1105,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Meta-Llama-3-8B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Meta-Llama-3-8B</a>",
- 1,
- "1.0_maltese",
- 26.81,
- 29.26,
- 24.36,
- 66.08,
- 48.06,
- 6.33,
- 13.02,
- 12.8,
- 12.03,
- 32.77,
- 10.3,
- 42.05,
- 18.66,
- 19.17,
- 0.18,
- 0.19,
- 34.89,
- 28.13,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama3",
- 8.03,
- 6400,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-1.7B-Instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-1.7B-Instruct</a>",
- 1,
- "1.0_english",
- 26.64,
- 29.29,
- 23.99,
- 68.98,
- 36.49,
- 6.33,
- 24.49,
- 10.16,
- 13.12,
- 38.3,
- 21.02,
- 54,
- 13.3,
- 10.5,
- 0,
- 0,
- 22.78,
- 14.34,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 1.66,
- 94,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-1.7B-Instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-1.7B-Instruct</a>",
- 1,
- "1.0_maltese",
- 25.89,
- 28.16,
- 23.61,
- 49.08,
- 52.01,
- 8.33,
- 20.27,
- 11.12,
- 17.72,
- 40.35,
- 21.62,
- 54.6,
- 14.5,
- 13.13,
- 0,
- 0,
- 17.22,
- 8.61,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 1.66,
- 94,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-xxl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-xxl</a>",
- 1,
- "1.0_maltese",
- 24.53,
- 33.36,
- 15.7,
- 74.94,
- 48.35,
- 6.33,
- 20.47,
- 16.73,
- 8.7,
- 26.93,
- 5.54,
- 30.66,
- 11.67,
- 13.25,
- 3.28,
- 2.69,
- 11.64,
- 6.54,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 13.95,
- 60,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-2b-instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-2b-instruct</a>",
- 1,
- "1.0_english",
- 24.41,
- 32.96,
- 15.87,
- 76.12,
- 52.35,
- 6.33,
- 21.28,
- 8.71,
- 4.2,
- 28.09,
- 3.44,
- 35.23,
- 3.32,
- 1.89,
- 0,
- 0,
- 18.92,
- 12.71,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 2.25,
- 25,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-13b-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-13b-hf</a>",
- 1,
- "1.0_english",
- 22.35,
- 28.17,
- 16.54,
- 60.2,
- 47.43,
- 9.98,
- 9.66,
- 13.57,
- 6.33,
- 23.11,
- 2.04,
- 23.54,
- 16.66,
- 15.94,
- 0,
- 0,
- 26.69,
- 19.4,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 13.02,
- 618,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-1.7B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-1.7B</a>",
- 1,
- "1.0_english",
- 22.31,
- 21.92,
- 22.7,
- 52.23,
- 20.9,
- 6.33,
- 18.52,
- 11.64,
- 16.44,
- 37.59,
- 20.91,
- 52.99,
- 12.39,
- 9.94,
- 0,
- 0,
- 19.4,
- 10.52,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 0,
- 104,
- true,
- "main"
- [
- "IT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-7b-chat-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-7b-chat-hf</a>",
- 1,
- "1.0_english",
- 22.17,
- 30.63,
- 13.71,
- 66.17,
- 44.26,
- 8.72,
- 24.54,
- 9.48,
- 3.78,
- 16.28,
- 2.49,
- 19.96,
- 13.97,
- 13.4,
- 0,
- 0,
- 25.69,
- 18.35,
- "instruction-tuned",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 6.74,
- 4670,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-7b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-7b</a>",
- 1,
- "1.0_maltese",
- 22.06,
- 23.82,
- 20.31,
- 52.5,
- 29.37,
- 6.37,
- 23.51,
- 7.34,
- 7.41,
- 29.12,
- 12.92,
- 42.32,
- 9.31,
- 7.91,
- 0.05,
- 0.05,
- 25.86,
- 20.73,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 7.77,
- 29,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-2b-instruct" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-2b-instruct</a>",
- 1,
- "1.0_maltese",
- 21.09,
- 25.03,
- 17.16,
- 70.53,
- 21.56,
- 6.37,
- 18.3,
- 8.37,
- 4.95,
- 30.3,
- 3.84,
- 36.22,
- 4.92,
- 2.19,
- 0,
- 0,
- 21.51,
- 14.36,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 2.25,
- 25,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-xxl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-xxl</a>",
- 1,
- "1.0_english",
- 21.07,
- 25.9,
- 16.25,
- 61.09,
- 46.39,
- 6.33,
- null,
- 15.68,
- 9.01,
- 31.26,
- 4.78,
- 29.56,
- 10.82,
- 10.78,
- 3.79,
- 3.15,
- 11.61,
- 6.48,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 13.95,
- 60,
- true,
- "main"
- [
- "IT/?",
- "<a target="_blank" href="https://huggingface.co/mistralai/Ministral-8B-Instruct-2410" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">mistralai/Ministral-8B-Instruct-2410</a>",
- 1,
- "1.0_english",
- 21.05,
- 27.45,
- 14.65,
- 70.92,
- 43.67,
- 6.33,
- null,
- 16.35,
- 3.93,
- 17.17,
- 1.44,
- 18.85,
- 14.43,
- 11.91,
- 0.79,
- 1.47,
- 30.94,
- 21.33,
- "instruction-tuned",
- "unknown",
- "?",
- "MistralForCausalLM",
- "?",
- "other",
- 8.02,
- 564,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/utter-project/EuroLLM-1.7B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">utter-project/EuroLLM-1.7B</a>",
- 1,
- "1.0_maltese",
- 20.82,
- 22.17,
- 19.48,
- 46.77,
- 34.34,
- 6.33,
- 13.92,
- 9.5,
- 10.26,
- 26.58,
- 19.45,
- 51.52,
- 13.95,
- 12.76,
- 0,
- 0,
- 13.96,
- 5.33,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 0,
- 104,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/CohereForAI/aya-23-8B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">CohereForAI/aya-23-8B</a>",
- 1,
- "1.0_english",
- 20.34,
- 29.31,
- 11.37,
- 68.3,
- 34.63,
- 6.33,
- 22.79,
- 14.49,
- 2.3,
- 13.09,
- 0.54,
- 11.6,
- 12.31,
- 8.23,
- 0,
- 0,
- 28.2,
- 19.83,
- "instruction-tuned",
- "none",
- 23,
- "CohereForCausalLM",
- "?",
- "cc-by-nc-4.0",
- 8.03,
- 425,
- true,
- "main"
- [
- "IT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-13b-chat-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-13b-chat-hf</a>",
- 1,
- "1.0_maltese",
- 17.89,
- 18.36,
- 17.41,
- 28.95,
- 35.9,
- 6.13,
- 7.9,
- 12.91,
- 6.05,
- 22.97,
- 3.86,
- 27.61,
- 19.8,
- 18.23,
- 0,
- 0,
- 25.8,
- 16.69,
- "instruction-tuned",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 13.02,
- 1105,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-large" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-large</a>",
- 1,
- "1.0_english",
- 17.77,
- 27.8,
- 7.75,
- 76.99,
- 21.06,
- 6.33,
- 18.68,
- 15.94,
- 1.12,
- 10.51,
- 0.22,
- 10.25,
- 13.82,
- 10.77,
- 5.38,
- 2.38,
- 1.79,
- 1.77,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 1.23,
- 49,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-7b-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-7b-hf</a>",
- 1,
- "1.0_english",
- 17.77,
- 22.56,
- 12.98,
- 36.29,
- 31.26,
- 6.33,
- 24.13,
- 14.8,
- 4.59,
- 16.98,
- 1.48,
- 19.32,
- 12.57,
- 10.28,
- 0,
- 0,
- 23,
- 16.02,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 6.74,
- 2213,
- true,
- "main"
- [
- "IT/?",
- "<a target="_blank" href="https://huggingface.co/mistralai/Ministral-8B-Instruct-2410" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">mistralai/Ministral-8B-Instruct-2410</a>",
- 1,
- "1.0_maltese",
- 17.69,
- 23.68,
- 11.7,
- 65.26,
- 23.74,
- 6.33,
- 9.02,
- 14.04,
- 3.28,
- 15.25,
- 1.6,
- 19.16,
- 14.72,
- 13.17,
- 0.95,
- 1.62,
- 16.57,
- 7.78,
- "instruction-tuned",
- "unknown",
- "?",
- "MistralForCausalLM",
- "?",
- "other",
- 8.02,
- 564,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-2b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-2b</a>",
- 1,
- "1.0_english",
- 17.48,
- 19.45,
- 15.51,
- 25.97,
- 41.14,
- 6.33,
- 14.59,
- 9.23,
- 3.73,
- 22.35,
- 7.1,
- 34.27,
- 8.15,
- 6.56,
- 0,
- 0,
- 20.19,
- 12.79,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 2.25,
- 24,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-7b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-7b1</a>",
- 1,
- "1.0_english",
- 17.3,
- 24.69,
- 9.9,
- 54.52,
- 41.59,
- 6.33,
- 7.71,
- 13.3,
- 1.67,
- 11.1,
- 0.91,
- 15.3,
- 12.66,
- 11.21,
- 0,
- 0,
- 20.97,
- 10.43,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 7.07,
- 203,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-2b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-2b</a>",
- 1,
- "1.0_english",
- 17.05,
- 21.32,
- 12.77,
- 30.5,
- 36.09,
- 6.33,
- 21.63,
- 12.08,
- 3.28,
- 14.28,
- 2.42,
- 23.72,
- 12.99,
- 13.14,
- 0.18,
- 0.23,
- 19.17,
- 12.63,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 2.61,
- 610,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-7b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-7b1</a>",
- 1,
- "1.0_english",
- 16.96,
- 26.9,
- 7.03,
- 57.48,
- 45.12,
- 6.33,
- 12.29,
- 13.3,
- 0.49,
- 7.65,
- 0.34,
- 9.31,
- 12.59,
- 12.85,
- 0.81,
- 1.08,
- 12.44,
- 4.5,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 7.07,
- 146,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-13b-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-13b-hf</a>",
- 1,
- "1.0_maltese",
- 16.84,
- 16.68,
- 16.99,
- 26.98,
- 30.53,
- 6.33,
- 7.06,
- 12.52,
- 5.43,
- 21.44,
- 2.24,
- 24.23,
- 16.6,
- 15.53,
- 0,
- 0,
- 30.11,
- 22.69,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 13.02,
- 618,
- true,
- "main"
- [
- "IT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-7b-chat-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-7b-chat-hf</a>",
- 1,
- "1.0_maltese",
- 16.09,
- 18.72,
- 13.45,
- 32.72,
- 34.91,
- 6.33,
- 9.8,
- 9.85,
- 3.09,
- 15.68,
- 3.05,
- 24.11,
- 15.31,
- 13.62,
- 0,
- 0,
- 22.04,
- 12.16,
- "instruction-tuned",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 6.74,
- 4670,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-1b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-1b1</a>",
- 1,
- "1.0_english",
- 15.91,
- 24.49,
- 7.33,
- 60.29,
- 23.39,
- 6.33,
- 17.8,
- 14.63,
- 0.87,
- 8.25,
- 0.24,
- 8.92,
- 12.4,
- 11.72,
- 2.05,
- 2.88,
- 11.97,
- 4.21,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.06,
- 33,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-4.5B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-4.5B</a>",
- 1,
- "1.0_english",
- 15.75,
- 20.58,
- 10.91,
- 56.35,
- 14.16,
- 6.37,
- 10.58,
- 15.41,
- 3.88,
- 15.81,
- 1,
- 15.64,
- 13.94,
- 9.88,
- 0,
- 0,
- 21.49,
- 9.18,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 5.08,
- 20,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-2.9B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-2.9B</a>",
- 1,
- "1.0_english",
- 15.53,
- 21.08,
- 9.98,
- 46.54,
- 25.79,
- 6.33,
- 13.49,
- 13.26,
- 3.41,
- 13.49,
- 1.12,
- 13.84,
- 12.79,
- 8.6,
- 0,
- 0,
- 21.58,
- 9.78,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 10,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-large" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-large</a>",
- 1,
- "1.0_maltese",
- 15.45,
- 22.04,
- 8.87,
- 66.81,
- 10.22,
- 6.33,
- 11.88,
- 14.97,
- 1.43,
- 10.3,
- 0.4,
- 11.49,
- 17.1,
- 11.9,
- 4.88,
- 2.48,
- 2.34,
- 2.96,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 1.23,
- 49,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-1.7B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-1.7B</a>",
- 1,
- "1.0_english",
- 15.09,
- 19.03,
- 11.15,
- 50.06,
- 15.77,
- 6.33,
- 10.44,
- 12.53,
- 3.53,
- 15.12,
- 0.95,
- 17.73,
- 13.39,
- 10.15,
- 0.04,
- 0.03,
- 21.48,
- 9.47,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 20,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/BSC-LT/salamandra-2b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">BSC-LT/salamandra-2b</a>",
- 1,
- "1.0_maltese",
- 15.05,
- 14.34,
- 15.76,
- 25.97,
- 27.53,
- 6.33,
- 4.49,
- 7.37,
- 3.53,
- 21.46,
- 8.14,
- 35.52,
- 9.55,
- 8.19,
- 0.01,
- 0.01,
- 19.32,
- 12.26,
- "pre-trained",
- "pre-training",
- 35,
- "LlamaForCausalLM",
- "?",
- "apache-2.0",
- 2.25,
- 24,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-3b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-3b</a>",
- 1,
- "1.0_english",
- 15,
- 22.63,
- 7.37,
- 49.34,
- 32.97,
- 6.33,
- 9.57,
- 14.95,
- 0.3,
- 5.91,
- 0.17,
- 7.74,
- 17.86,
- 17.54,
- 0.39,
- 0.46,
- 13.18,
- 4.86,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 3,
- 81,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-7b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-7b1</a>",
- 1,
- "1.0_maltese",
- 14.72,
- 21.79,
- 7.64,
- 49.06,
- 37.13,
- 6.33,
- 3.62,
- 12.82,
- 0.25,
- 10.46,
- 0.51,
- 16.05,
- 7.57,
- 8.37,
- 0,
- 0,
- 11.77,
- 4.13,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 7.07,
- 146,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-2b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-2b</a>",
- 1,
- "1.0_maltese",
- 14.65,
- 15.59,
- 13.71,
- 25.97,
- 15.21,
- 6.13,
- 16.46,
- 14.18,
- 2.28,
- 12.44,
- 2.24,
- 22.85,
- 12.5,
- 10.43,
- 0.24,
- 0.35,
- 27.55,
- 20.42,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 2.61,
- 610,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-small" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-small</a>",
- 1,
- "1.0_english",
- 14.63,
- 21.71,
- 7.55,
- 54.38,
- 15.24,
- 6.33,
- 18.94,
- 13.69,
- 2.49,
- 16.69,
- 0.59,
- 14.6,
- 4.99,
- 3.92,
- 3.89,
- 1.33,
- 0.64,
- 0.14,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0.3,
- 31,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-xl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-xl</a>",
- 1,
- "1.0_maltese",
- 14.62,
- 16.54,
- 12.7,
- 26.98,
- 20.55,
- 6.33,
- 13.65,
- 15.19,
- 4.17,
- 18.54,
- 0.66,
- 17.14,
- 20.16,
- 17.49,
- 3.7,
- 2.94,
- 12.91,
- 4.7,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 3.74,
- 32,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-1b7" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-1b7</a>",
- 1,
- "1.0_english",
- 14.08,
- 21.49,
- 6.68,
- 39.36,
- 35.51,
- 6.33,
- 13.09,
- 13.15,
- 0.37,
- 5.56,
- 0.11,
- 6.07,
- 15.45,
- 14.97,
- 0.36,
- 0.4,
- 13.4,
- 5.92,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.72,
- 23,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-7.5B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-7.5B</a>",
- 1,
- "1.0_english",
- 14.03,
- 17.83,
- 10.23,
- 32.85,
- 26.11,
- 6.33,
- 9.19,
- 14.68,
- 3.17,
- 12.72,
- 1.1,
- 16.45,
- 12.91,
- 10.71,
- 0,
- 0,
- 20.81,
- 9.06,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 59,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-564M" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-564M</a>",
- 1,
- "1.0_english",
- 13.95,
- 16.41,
- 11.49,
- 48.02,
- 2.2,
- 6.33,
- 10.93,
- 14.54,
- 2.76,
- 19.11,
- 0.68,
- 17.29,
- 11.74,
- 6.36,
- 0.02,
- 0.01,
- 20.49,
- 9.32,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 53,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-560m" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-560m</a>",
- 1,
- "1.0_english",
- 13.9,
- 22.74,
- 5.07,
- 51.11,
- 34.07,
- 6.33,
- 7.54,
- 14.63,
- 0.19,
- 4.58,
- 0.03,
- 5.01,
- 10.67,
- 9.71,
- 0.72,
- 0.98,
- 11.63,
- 4.1,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 0.56,
- 131,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-1.7B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-1.7B</a>",
- 1,
- "1.0_maltese",
- 13.86,
- 14.63,
- 13.1,
- 46.2,
- 2.2,
- 6.33,
- 5.64,
- 12.77,
- 3.09,
- 18.35,
- 1.07,
- 20.8,
- 14.19,
- 8.22,
- 2.34,
- 2.59,
- 21.31,
- 9.59,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 20,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/MBZUAI/bactrian-x-bloom-7b1-lora" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MBZUAI/bactrian-x-bloom-7b1-lora</a>",
- 1,
- "1.0_english",
- 13.68,
- 19.04,
- 8.31,
- 53.23,
- 23.84,
- 6.33,
- 4.36,
- 7.46,
- 0.6,
- 10.3,
- 0.63,
- 16.52,
- 10.97,
- 9.25,
- 0,
- 0,
- 5.23,
- 3.77,
- "instruction-tuned",
- "none",
- 77,
- "BloomForCausalLM",
- "?",
- "mit",
- 0,
- "?",
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/DAMO-NLP-MT/polylm-1.7b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">DAMO-NLP-MT/polylm-1.7b</a>",
- 1,
- "1.0_english",
- 13.61,
- 18.63,
- 8.6,
- 52.08,
- 19.28,
- 6.33,
- 5.08,
- 10.41,
- 0.39,
- 11.56,
- 0.28,
- 16.49,
- 10.74,
- 8.94,
- 0,
- 0,
- 11.88,
- 4.19,
- "pre-trained",
- "none",
- 18,
- "GPT2LMHeadModel",
- "?",
- "apache-2.0",
- 0,
- 11,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-xl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-xl</a>",
- 1,
- "1.0_english",
- 13.56,
- 18.89,
- 8.23,
- 27.97,
- 30.23,
- 6.33,
- 15.43,
- 14.51,
- 1.36,
- 10.29,
- 0.11,
- 7.06,
- 18.14,
- 17.11,
- 4.69,
- 1.14,
- 12.28,
- 4.51,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 3.74,
- 32,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/ai-forever/mGPT-13B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">ai-forever/mGPT-13B</a>",
- 1,
- "1.0_english",
- 13.39,
- 20.6,
- 6.17,
- 41.8,
- 47.67,
- 6.33,
- null,
- 7.22,
- 0.98,
- 9.19,
- 0.41,
- 11.58,
- 9.84,
- 6.1,
- 0.06,
- 0.07,
- 1,
- 0.16,
- "pre-trained",
- "none",
- 61,
- "GPT2LMHeadModel",
- "?",
- "mit",
- 0,
- 49,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-564M" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-564M</a>",
- 1,
- "1.0_maltese",
- 13.16,
- 13.79,
- 12.53,
- 39.88,
- 2.2,
- 6.33,
- 5.81,
- 14.76,
- 2.94,
- 19.63,
- 0.53,
- 18.49,
- 13.23,
- 7.2,
- 2.72,
- 3.09,
- 18.66,
- 8.24,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 53,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-3b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-3b</a>",
- 1,
- "1.0_english",
- 12.85,
- 16.54,
- 9.17,
- 41.14,
- 14.07,
- 6.33,
- 7.19,
- 13.95,
- 1.79,
- 10.71,
- 0.57,
- 14.91,
- 12.5,
- 10.58,
- 0,
- 0,
- 18.12,
- 7.73,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 3,
- 93,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-7b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-7b1</a>",
- 1,
- "1.0_maltese",
- 12.84,
- 16.42,
- 9.26,
- 44.62,
- 15.56,
- 6.33,
- 2.07,
- 13.52,
- 0.48,
- 10.91,
- 0.44,
- 16.72,
- 12.42,
- 11.37,
- 0,
- 0,
- 15.82,
- 6.27,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 7.07,
- 203,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/CohereForAI/aya-23-8B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">CohereForAI/aya-23-8B</a>",
- 1,
- "1.0_maltese",
- 12.74,
- 17.15,
- 8.33,
- 29.2,
- 32.53,
- 6.33,
- 5.42,
- 12.29,
- 1.66,
- 11.81,
- 0.76,
- 13.28,
- 11.99,
- 8.27,
- 0.01,
- 0.01,
- 12.57,
- 4.55,
- "instruction-tuned",
- "none",
- 23,
- "CohereForCausalLM",
- "?",
- "cc-by-nc-4.0",
- 8.03,
- 425,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/DAMO-NLP-MT/polylm-13b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">DAMO-NLP-MT/polylm-13b</a>",
- 1,
- "1.0_english",
- 12.62,
- 13.25,
- 11.99,
- 25.97,
- 21.6,
- 6.33,
- null,
- 12.33,
- 6.46,
- 19.12,
- 1.78,
- 19.78,
- 10.36,
- 6.2,
- 0,
- 0,
- 19.94,
- 10.66,
- "pre-trained",
- "none",
- 18,
- "PolyLMHeadModel",
- "?",
- "apache-2.0",
- 0,
- 53,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/DAMO-NLP-MT/polylm-13b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">DAMO-NLP-MT/polylm-13b</a>",
- 1,
- "1.0_maltese",
- 12.51,
- 15.4,
- 9.63,
- 42.87,
- 2.2,
- 6.33,
- 12.39,
- 13.23,
- 1.91,
- 12.67,
- 1.5,
- 18.93,
- 12.44,
- 9.5,
- 0,
- 0,
- 11.7,
- 4.09,
- "pre-trained",
- "none",
- 18,
- "PolyLMHeadModel",
- "?",
- "apache-2.0",
- 0,
- 53,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-3b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-3b</a>",
- 1,
- "1.0_maltese",
- 12.5,
- 16.74,
- 8.25,
- 44.26,
- 6.89,
- 6.33,
- 11.26,
- 14.95,
- 0.21,
- 10.53,
- 0.09,
- 16.67,
- 10.05,
- 11.43,
- 0,
- 0,
- 11.6,
- 4.03,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 3,
- 81,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/meta-llama/Llama-2-7b-hf" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">meta-llama/Llama-2-7b-hf</a>",
- 1,
- "1.0_maltese",
- 12.23,
- 11.07,
- 13.38,
- 25.97,
- 2.2,
- 6.33,
- 13.64,
- 7.23,
- 3.32,
- 15.19,
- 1.56,
- 19.71,
- 13.99,
- 12.61,
- 0,
- 0,
- 26.84,
- 18,
- "pre-trained",
- "unknown",
- "?",
- "LlamaForCausalLM",
- "?",
- "llama2",
- 6.74,
- 2213,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-base" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-base</a>",
- 1,
- "1.0_english",
- 12.15,
- 19.2,
- 5.11,
- 35.07,
- 19.52,
- 6.33,
- 24.32,
- 10.75,
- 0.41,
- 5.68,
- 0.02,
- 3.92,
- 13.28,
- 9.18,
- 2.63,
- 0.38,
- 8.42,
- 2.27,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0.58,
- 32,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-1b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-1b1</a>",
- 1,
- "1.0_maltese",
- 11.98,
- 16.95,
- 7.01,
- 56.25,
- 2.2,
- 6.33,
- 5.39,
- 14.61,
- 0.16,
- 10.02,
- 0.09,
- 15.1,
- 6.87,
- 5.74,
- 0,
- 0,
- 10.43,
- 3.07,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.06,
- 33,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-560m" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-560m</a>",
- 1,
- "1.0_english",
- 11.89,
- 16.16,
- 7.61,
- 50,
- 4.41,
- 6.33,
- 4.24,
- 15.84,
- 1.01,
- 9.84,
- 0.36,
- 13.19,
- 11.19,
- 8.34,
- 0,
- 0,
- 11.04,
- 3.82,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 0.56,
- 369,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/MaLA-LM/mala-500-10b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MaLA-LM/mala-500-10b</a>",
- 1,
- "1.0_english",
- 11.83,
- 15.79,
- 7.87,
- 25.97,
- 39.28,
- 6.33,
- 3.25,
- 4.15,
- 0.03,
- 11.1,
- 0.06,
- 13.67,
- 9.82,
- 5.5,
- 0,
- 0,
- 13.15,
- 4.77,
- "pre-trained",
- "pre-training",
- 511,
- "LlamaForCausalLM",
- "?",
- "llama2",
- 0,
- 6,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-7.5B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-7.5B</a>",
- 1,
- "1.0_maltese",
- 11.74,
- 10.88,
- 12.6,
- 25.97,
- 2.2,
- 6.33,
- 5.62,
- 14.3,
- 3.46,
- 15.46,
- 0.72,
- 19.55,
- 14.8,
- 8.87,
- 0.84,
- 1.17,
- 23.99,
- 12.04,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 59,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-4.5B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-4.5B</a>",
- 1,
- "1.0_maltese",
- 11.49,
- 11.22,
- 11.75,
- 25.97,
- 2.2,
- 6.33,
- 7.02,
- 14.6,
- 3.1,
- 15.58,
- 0.66,
- 17.93,
- 13.6,
- 9.53,
- 0.45,
- 0.43,
- 22.87,
- 11.19,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 5.08,
- 20,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/facebook/xglm-2.9B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">facebook/xglm-2.9B</a>",
- 1,
- "1.0_maltese",
- 11.36,
- 11.04,
- 11.68,
- 25.97,
- 2.2,
- 6.33,
- 6.53,
- 14.19,
- 2.35,
- 15.1,
- 0.35,
- 16.73,
- 13.96,
- 7.54,
- 1.4,
- 1.86,
- 22.14,
- 10.74,
- "pre-trained",
- "none",
- 30,
- "XGLMForCausalLM",
- "?",
- "mit",
- 0,
- 10,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-1b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-1b1</a>",
- 1,
- "1.0_english",
- 11.33,
- 13.87,
- 8.79,
- 41.14,
- 2.2,
- 6.33,
- 5.52,
- 14.19,
- 0.4,
- 10.04,
- 0.27,
- 14.6,
- 11.63,
- 7.97,
- 0,
- 0,
- 18.12,
- 7.66,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.06,
- 64,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-1b7" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-1b7</a>",
- 1,
- "1.0_english",
- 11.27,
- 13.78,
- 8.75,
- 39.36,
- 2.2,
- 6.33,
- 5.97,
- 15.05,
- 0.74,
- 9.73,
- 0.43,
- 14.68,
- 11.32,
- 7.72,
- 0,
- 0,
- 17.31,
- 8.03,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.72,
- 122,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-large" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-large</a>",
- 1,
- "1.0_english",
- 10.99,
- 14.36,
- 7.62,
- 49.62,
- 2.2,
- 6.33,
- 2.12,
- 11.56,
- 0.18,
- 9.01,
- 0.1,
- 12.37,
- 10.6,
- 3.43,
- 3.18,
- 4.4,
- 6.2,
- 1.73,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 101,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/ai-forever/mGPT-13B" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">ai-forever/mGPT-13B</a>",
- 1,
- "1.0_maltese",
- 10.98,
- 14.68,
- 7.27,
- 40.66,
- 14.03,
- 6.33,
- 5.24,
- 7.14,
- 0.56,
- 10.82,
- 0.35,
- 16.06,
- 9.13,
- 5.44,
- 0.05,
- 0.11,
- 1.15,
- 0.24,
- "pre-trained",
- "none",
- 61,
- "GPT2LMHeadModel",
- "?",
- "mit",
- 0,
- 49,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-xxl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-xxl</a>",
- 1,
- "1.0_english",
- 10.9,
- 14.61,
- 7.19,
- 48.02,
- 2.2,
- 6.41,
- 3.89,
- 12.53,
- 0.2,
- 8.22,
- 0.13,
- 10.96,
- 9.02,
- 3.11,
- 4.26,
- 4.36,
- 8.73,
- 3.39,
- "pre-trained",
- "pre-training",
- 101,
- "T5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 70,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-560m" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-560m</a>",
- 1,
- "1.0_maltese",
- 10.69,
- 14.02,
- 7.36,
- 42.42,
- 2.2,
- 6.33,
- 3.02,
- 16.13,
- 0.19,
- 9.98,
- 0.06,
- 14.9,
- 9.62,
- 6.82,
- 0,
- 0,
- 7.23,
- 2.29,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 0.56,
- 369,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-1b7" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-1b7</a>",
- 1,
- "1.0_maltese",
- 10.52,
- 13.52,
- 7.51,
- 39.36,
- 2.2,
- 6.33,
- 4.38,
- 15.34,
- 0.17,
- 9.98,
- 0.08,
- 14.95,
- 10.33,
- 7.22,
- 0,
- 0,
- 7.16,
- 2.31,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.72,
- 122,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-1b1" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-1b1</a>",
- 1,
- "1.0_maltese",
- 10.4,
- 13.13,
- 7.66,
- 39.36,
- 2.2,
- 6.33,
- 2.73,
- 15.01,
- 0.17,
- 9.89,
- 0.07,
- 14.84,
- 11.09,
- 8.43,
- 0,
- 0,
- 8.43,
- 2.5,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.06,
- 64,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/DAMO-NLP-MT/polylm-1.7b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">DAMO-NLP-MT/polylm-1.7b</a>",
- 1,
- "1.0_maltese",
- 10.38,
- 12.41,
- 8.36,
- 39.36,
- 2.2,
- 6.33,
- 3.78,
- 10.39,
- 0.15,
- 11.26,
- 0.08,
- 16.02,
- 10.14,
- 6.62,
- 0,
- 0,
- 12.24,
- 4.36,
- "pre-trained",
- "none",
- 18,
- "GPT2LMHeadModel",
- "?",
- "apache-2.0",
- 0,
- 11,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/MBZUAI/bactrian-x-bloom-7b1-lora" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MBZUAI/bactrian-x-bloom-7b1-lora</a>",
- 1,
- "1.0_maltese",
- 10.26,
- 12.48,
- 8.05,
- 42.6,
- 2.2,
- 6.33,
- 3.69,
- 7.56,
- 0.29,
- 10.64,
- 0.12,
- 16.65,
- 9.12,
- 5.65,
- 0,
- 0,
- 3.79,
- 3.84,
- "instruction-tuned",
- "none",
- 77,
- "BloomForCausalLM",
- "?",
- "mit",
- 0,
- "?",
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-base" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-base</a>",
- 1,
- "1.0_maltese",
- 10.23,
- 12.69,
- 7.76,
- 25.97,
- 6.68,
- 6.33,
- 11.57,
- 12.92,
- 1.49,
- 11.36,
- 0.26,
- 11.65,
- 11.84,
- 9.84,
- 3.47,
- 1.6,
- 8.73,
- 2.33,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0.58,
- 32,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-1b7" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-1b7</a>",
- 1,
- "1.0_maltese",
- 10.07,
- 13.56,
- 6.57,
- 39.15,
- 2.2,
- 6.33,
- 5.92,
- 14.22,
- 0.27,
- 9.9,
- 0.06,
- 14.61,
- 6.09,
- 5.48,
- 0,
- 0,
- 6.91,
- 2.25,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 1.72,
- 23,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-xl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-xl</a>",
- 1,
- "1.0_english",
- 10,
- 11.8,
- 8.19,
- 39.36,
- 2.2,
- 6.33,
- 1.24,
- 9.87,
- 0.33,
- 11.03,
- 0.21,
- 14.99,
- 8.91,
- 2.95,
- 4.3,
- 4.44,
- 5.73,
- 1.59,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 25,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/ai-forever/mGPT" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">ai-forever/mGPT</a>",
- 1,
- "1.0_maltese",
- 9.92,
- 12.34,
- 7.51,
- 41.14,
- 2.2,
- 6.33,
- 4.7,
- 7.32,
- 0.45,
- 10.74,
- 0.09,
- 16.71,
- 9.25,
- 6.29,
- 0.15,
- 0.26,
- 1.35,
- 0.61,
- "pre-trained",
- "none",
- 61,
- "GPT2LMHeadModel",
- "?",
- "apache-2.0",
- 0,
- 270,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/ai-forever/mGPT" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">ai-forever/mGPT</a>",
- 1,
- "1.0_english",
- 9.87,
- 11.78,
- 7.95,
- 39.36,
- 2.2,
- 6.33,
- 3.7,
- 7.34,
- 1.57,
- 11.62,
- 1,
- 16.87,
- 10.04,
- 6.76,
- 0.16,
- 0.56,
- 1.43,
- 0.67,
- "pre-trained",
- "none",
- 61,
- "GPT2LMHeadModel",
- "?",
- "apache-2.0",
- 0,
- 270,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-xl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-xl</a>",
- 1,
- "1.0_maltese",
- 9.85,
- 11.74,
- 7.96,
- 39.15,
- 2.2,
- 6.37,
- 1.24,
- 9.72,
- 0.24,
- 10.24,
- 0.19,
- 14.45,
- 9.19,
- 3.4,
- 4.19,
- 4.34,
- 5.45,
- 1.56,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 25,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloom-3b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloom-3b</a>",
- 1,
- "1.0_maltese",
- 9.77,
- 10.81,
- 8.73,
- 26.98,
- 2.2,
- 6.33,
- 4.8,
- 13.75,
- 0.22,
- 10.64,
- 0.13,
- 16.71,
- 12.16,
- 10.11,
- 0,
- 0,
- 11.88,
- 4.12,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 3,
- 93,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/MBZUAI/bactrian-x-llama-13b-lora" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MBZUAI/bactrian-x-llama-13b-lora</a>",
- 1,
- "1.0_english",
- 9.12,
- 9.65,
- 8.59,
- 25.97,
- 2.2,
- 6.33,
- 3.62,
- 10.14,
- 1.02,
- 11.99,
- 0.68,
- 15.97,
- 11.73,
- 7.77,
- 0.07,
- 0.07,
- 8.24,
- 3.2,
- "instruction-tuned",
- "none",
- 52,
- "LlamaForCausalLM",
- "?",
- "mit",
- 0,
- 3,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/MaLA-LM/mala-500-10b" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MaLA-LM/mala-500-10b</a>",
- 1,
- "1.0_maltese",
- 9,
- 9.43,
- 8.57,
- 25.97,
- 2.2,
- 8.22,
- 4.97,
- 5.78,
- 0.05,
- 13.67,
- 0.02,
- 14.06,
- 10.47,
- 6.71,
- 0,
- 0,
- 13.12,
- 4.67,
- "pre-trained",
- "pre-training",
- 511,
- "LlamaForCausalLM",
- "?",
- "llama2",
- 0,
- 6,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-xxl" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-xxl</a>",
- 1,
- "1.0_maltese",
- 8.98,
- 10.34,
- 7.62,
- 27.63,
- 2.2,
- 5.46,
- 3.88,
- 12.55,
- 0.24,
- 9.01,
- 0.19,
- 12.45,
- 9,
- 3.26,
- 4.25,
- 4.45,
- 8.42,
- 3.18,
- "pre-trained",
- "pre-training",
- 101,
- "T5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 70,
- true,
- "main"
- [
- "IT/PT",
- "<a target="_blank" href="https://huggingface.co/bigscience/mt0-small" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/mt0-small</a>",
- 1,
- "1.0_maltese",
- 8.67,
- 13,
- 4.34,
- 27.63,
- 9.33,
- 6.33,
- 8.11,
- 13.6,
- 0.53,
- 7.54,
- 0.04,
- 7.79,
- 4.51,
- 2.01,
- 4.13,
- 1.71,
- 1,
- 0.16,
- "instruction-tuned",
- "pre-training",
- 120,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0.3,
- 31,
- true,
- "main"
- [
- "PT/NO",
- "<a target="_blank" href="https://huggingface.co/bigscience/bloomz-560m" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">bigscience/bloomz-560m</a>",
- 1,
- "1.0_maltese",
- 8.64,
- 10.64,
- 6.64,
- 25.97,
- 2.2,
- 6.33,
- 3.78,
- 14.92,
- 0.2,
- 9.89,
- 0.06,
- 14.84,
- 6.19,
- 4.2,
- 0,
- 0.01,
- 6.97,
- 2.26,
- "pre-trained",
- "none",
- 46,
- "BloomForCausalLM",
- "?",
- "bigscience-bloom-rail-1.0",
- 0.56,
- 131,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/MBZUAI/bactrian-x-llama-13b-lora" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MBZUAI/bactrian-x-llama-13b-lora</a>",
- 1,
- "1.0_maltese",
- 8.59,
- 9.52,
- 7.66,
- 25.97,
- 2.2,
- 6.33,
- 3.95,
- 9.15,
- 1.08,
- 11.42,
- 0.38,
- 16.55,
- 7.99,
- 4.36,
- 0.17,
- 0.22,
- 6.44,
- 2.09,
- "instruction-tuned",
- "none",
- 52,
- "LlamaForCausalLM",
- "?",
- "mit",
- 0,
- 3,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-base" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-base</a>",
- 1,
- "1.0_english",
- 8.28,
- 11.96,
- 4.6,
- 35.5,
- 2.78,
- 10.27,
- 4.11,
- 7.16,
- 0.41,
- 4.69,
- 0.09,
- 5.95,
- 6.06,
- 6.98,
- 0.33,
- 0.85,
- 5.93,
- 5.43,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 253,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-base" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-base</a>",
- 1,
- "1.0_maltese",
- 8.02,
- 11.55,
- 4.5,
- 37.41,
- 2.78,
- 7.29,
- 3.03,
- 7.23,
- 0.56,
- 4.44,
- 0.07,
- 5.64,
- 5.86,
- 5.1,
- 0.31,
- 0.81,
- 5.63,
- 5.74,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 253,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/MBZUAI/bactrian-x-llama-7b-lora" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MBZUAI/bactrian-x-llama-7b-lora</a>",
- 1,
- "1.0_english",
- 5.94,
- 10.89,
- 0.98,
- 25.97,
- 6.99,
- 8.98,
- 6.05,
- 6.48,
- 0.01,
- 1.55,
- 0,
- 1.4,
- 1.95,
- 0.42,
- 1.2,
- 0.01,
- 0.85,
- 0.01,
- "instruction-tuned",
- "none",
- 52,
- "LlamaForCausalLM",
- "?",
- "mit",
- 0,
- 4,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-small" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-small</a>",
- 1,
- "1.0_maltese",
- 5.67,
- 9.3,
- 2.04,
- 25.97,
- 2.43,
- 3.73,
- 5.78,
- 8.58,
- 0.06,
- 1.95,
- 0.02,
- 2.2,
- 1.59,
- 0.64,
- 0.2,
- 0.5,
- 5.57,
- 3.94,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 173,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-small" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-small</a>",
- 1,
- "1.0_english",
- 5.61,
- 9.24,
- 1.98,
- 25.97,
- 2.43,
- 3.73,
- 5.78,
- 8.29,
- 0.06,
- 1.78,
- 0.01,
- 1.98,
- 1.5,
- 0.64,
- 0.21,
- 0.52,
- 5.74,
- 4.12,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 173,
- true,
- "main"
- [
- "IT/NO",
- "<a target="_blank" href="https://huggingface.co/MBZUAI/bactrian-x-llama-7b-lora" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">MBZUAI/bactrian-x-llama-7b-lora</a>",
- 1,
- "1.0_maltese",
- 5.32,
- 9.5,
- 1.14,
- 25.97,
- 2.78,
- 5.87,
- 6.4,
- 6.5,
- 0.01,
- 1.6,
- 0,
- 1.88,
- 2.18,
- 0.5,
- 1.17,
- 0.03,
- 0.77,
- 0.01,
- "instruction-tuned",
- "none",
- 52,
- "LlamaForCausalLM",
- "?",
- "mit",
- 0,
- 4,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-2b-it" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-2b-it</a>",
- 1,
- "1.0_english",
- 2.02,
- 4.03,
- 0,
- null,
- null,
- null,
- 7.61,
- 12.56,
- null,
- null,
- null,
- null,
- null,
- null,
- null,
- null,
- null,
- null,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 2.61,
- 1240,
- true,
- "main"
- [
- "PT/?",
- "<a target="_blank" href="https://huggingface.co/google/gemma-2-2b-it" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/gemma-2-2b-it</a>",
- 1,
- "1.0_maltese",
- 1.62,
- 3.23,
- 0,
- null,
- null,
- null,
- 6.57,
- 9.6,
- null,
- null,
- null,
- null,
- null,
- null,
- null,
- null,
- null,
- null,
- "pre-trained",
- "unknown",
- "?",
- "Gemma2ForCausalLM",
- "?",
- "gemma",
- 2.61,
- 1240,
- true,
- "main"
- [
- "PT/PT",
- "<a target="_blank" href="https://huggingface.co/google/mt5-large" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">google/mt5-large</a>",
- 1,
- "1.0_maltese",
- 1.37,
- 2.75,
- 0,
- null,
- null,
- null,
- 2.12,
- 11.61,
- null,
- null,
- null,
- null,
- null,
- null,
- null,
- null,
- null,
- null,
- "pre-trained",
- "pre-training",
- 101,
- "MT5ForConditionalGeneration",
- "?",
- "apache-2.0",
- 0,
- 101,
- true,
- "main"
- [
- "metadata": null
MELABench evaluates language model capabilities on Maltese. Currently, the following tasks are supported:
NLU:
NLG:
The leaderboard is developed and maintained by people managing MLRS. We plan to expand our initial work with more tasks, if you would like to contribute your data, please reach out! If you would like to include results for models/setups we did not include, we also accept submissions.
This work was introduced in MELABenchv1: Benchmarking Large Language Models against Smaller Fine-Tuned Models for Low-Resource Maltese NLP.
To include new results on this benchmark, follow the instructions on our GitHub Repository. You can then upload the output files which should include the configuration/results file and all the prediction files. In addition, we ask for additional metadata about model training.
model | revision | precision | n_shot | prompt_version | seed | status |
|---|---|---|---|---|---|---|
main | bfloat16 | 0 | 1.0_english | 0 | FINISHED |
model | revision | precision | n_shot | prompt_version | seed | status |
|---|---|---|---|---|---|---|
model | revision | precision | n_shot | prompt_version | seed | status |
|---|
model | revision | precision | n_shot | prompt_version | seed | status |
|---|---|---|---|---|---|---|
model | revision | precision | n_shot | prompt_version | seed | status |
|---|
โ๏ธโจ Submit your model here!
How to model is trained.
The last stage of training in which Maltese was included.