File size: 3,112 Bytes
4c59875 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
#feel free to correct these categories, I think size should also be added
model_info = {
"meta-llama-Meta-Llama-3-70B": {
"link": "https://huggingface.co/meta-llama/Meta-Llama-3-70B",
"tuning": "π’" # Pre-trained
},
"meta-llama-Meta-Llama-3-8B": {
"link": "https://huggingface.co/meta-llama/Meta-Llama-3-8B",
"tuning": "π’" # Pre-trained
},
"01-ai-Yi-1.5-34B": {
"link": "https://huggingface.co/01-ai/Yi-1.5-34B",
"tuning": "πΆ" # Fine-tuned on task specific dataset
},
"aaditya-Llama3-OpenBioLLM-70B": {
"link": "https://huggingface.co/aaditya/Llama3-OpenBioLLM-70B",
"tuning": "πΆ" # Fine-tuned on task specific dataset
},
"CohereForAI-aya-23-35B": {
"link": "https://huggingface.co/CohereForAI/aya-23-35B",
"tuning": "πΆ" # Fine-tuned on task specific dataset
},
"CohereForAI-c4ai-command-r-plus": {
"link": "https://huggingface.co/CohereForAI/c4ai-command-r-plus",
"tuning": "π¬" # Chat-model (RLHF, DPO, IFT, etc.)
},
"johnsnowlabs-JSL-MedLlama-3-8B-v9": {
"link": "https://huggingface.co/johnsnowlabs/JSL-MedLlama-3-8B-v9",
"tuning": "πΆ" # Fine-tuned on task specific dataset
},
"meta-llama-Llama-2-70B-hf": {
"link": "https://huggingface.co/meta-llama/Llama-2-70B-hf",
"tuning": "π’" # Pre-trained
},
"meta-llama-Llama-2-7b-hf": {
"link": "https://huggingface.co/meta-llama/Llama-2-7b-hf",
"tuning": "π’" # Pre-trained
},
"microsoft-phi-1_5": {
"link": "https://huggingface.co/microsoft/phi-1_5",
"tuning": "π’" # Pre-trained
},
"microsoft-phi-1": {
"link": "https://huggingface.co/microsoft/phi-1",
"tuning": "π’" # Pre-trained
},
"microsoft-phi-2": {
"link": "https://huggingface.co/microsoft/phi-2",
"tuning": "π’" # Pre-trained
},
"microsoft-Phi-3-medium-4k-instruct": {
"link": "https://huggingface.co/microsoft/Phi-3-medium-4k-instruct",
"tuning": "π¬" # Chat-model (RLHF, DPO, IFT, etc.)
},
"mistralai-Mistral-7B-v0.3": {
"link": "https://huggingface.co/mistralai/Mistral-7B-v0.3",
"tuning": "π’" # Continuously pre-trained
},
"mistralai-Mixtral-8x22B-v0.1": {
"link": "https://huggingface.co/mistralai/Mixtral-8x22B-v0.1",
"tuning": "π’" # Continuously pre-trained
},
"mistralai-Mixtral-8x7B-v0.1": {
"link": "https://huggingface.co/mistralai/Mixtral-8x7B-v0.1",
"tuning": "π’" # Continuously pre-trained
},
"ProbeMedicalYonseiMAILab-medllama3-v20": {
"link": "https://huggingface.co/ProbeMedicalYonseiMAILab/medllama3-v20",
"tuning": "πΆ" # Fine-tuned on task specific dataset
},
"Qwen-Qwen2-72B": {
"link": "https://huggingface.co/Qwen/Qwen2-72B",
"tuning": "π’" # Pre-trained
},
"Qwen-Qwen2-7B": {
"link": "https://huggingface.co/Qwen/Qwen2-7B",
"tuning": "π’" # Pre-trained
},
}
|