llm-api-hf / constants /models.py
karim23657's picture
Update constants/models.py
7670e16 verified
MODEL_MAP = {
"mixtral-8x7b": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"default": "meta-llama/Llama-3.3-70B-Instruct",
"Llama-3.3-70B-Instruct": "meta-llama/Llama-3.3-70B-Instruct",
"Qwen2.5-72B-Instruct": "Qwen/Qwen2.5-72B-Instruct",
"c4ai-command-r-plus-08-2024": "CohereForAI/c4ai-command-r-plus-08-2024",
"DeepSeek-R1-Distill-Qwen-32B": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
"Llama-3.1-Nemotron-70B-Instruct-HF": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
"QwQ-32B-Preview": "Qwen/QwQ-32B-Preview",
"Qwen2.5-Coder-32B-Instruct": "Qwen/Qwen2.5-Coder-32B-Instruct",
"Llama-3.2-11B-Vision-Instruct": "meta-llama/Llama-3.2-11B-Vision-Instruct",
"Hermes-3-Llama-3.1-8B": "NousResearch/Hermes-3-Llama-3.1-8B",
"Mistral-Nemo-Instruct-2407": "mistralai/Mistral-Nemo-Instruct-2407",
"Phi-3.5-mini-instruct": "microsoft/Phi-3.5-mini-instruct",
"DeepSeek-V3-0324": "deepseek-ai/DeepSeek-V3-0324",
"nous-mixtral-8x7b": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
"mistral-7b": "mistralai/Mistral-7B-Instruct-v0.2",
"yi-1.5-34b": "01-ai/Yi-1.5-34B-Chat",
"gemma-7b": "google/gemma-1.1-7b-it",
}
# {
# "mixtral-8x7b": "mistralai/Mixtral-8x7B-Instruct-v0.1", # [Recommended]
# "nous-mixtral-8x7b": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
# "mistral-7b": "mistralai/Mistral-7B-Instruct-v0.2",
# "yi-1.5-34b": "01-ai/Yi-1.5-34B-Chat",
# "gemma-7b": "google/gemma-1.1-7b-it",
# # "openchat-3.5": "openchat/openchat-3.5-0106",
# # "command-r-plus": "CohereForAI/c4ai-command-r-plus",
# # "llama3-70b": "meta-llama/Meta-Llama-3-70B-Instruct",
# # "zephyr-141b": "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
# "default": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
# }
AVAILABLE_MODELS = list(MODEL_MAP.keys())
PRO_MODELS = ["command-r-plus", "llama3-70b", "zephyr-141b"]
STOP_SEQUENCES_MAP = {
# https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1/blob/main/tokenizer_config.json#L33
"mixtral-8x7b": "</s>",
# https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO/blob/main/tokenizer_config.json#L50
"nous-mixtral-8x7b": "<|im_end|>",
# https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2/blob/main/tokenizer_config.json#L33
"mistral-7b": "</s>",
# https://huggingface.co/01-ai/Yi-1.5-34B-Chat/blob/main/tokenizer_config.json#L42
"yi-1.5-34b": "<|im_end|>",
# https://huggingface.co/google/gemma-1.1-7b-it/blob/main/tokenizer_config.json#L1509
"gemma-7b": "<eos>",
# https://huggingface.co/huihui-ai/Llama-3.3-70B-Instruct-abliterated/blob/fa13334669544bab573e0e5313cad629a9c02e2c/tokenizer_config.json#L2055
"Llama-3.3-70B-Instruct": "<|eot_id|>",
# https://huggingface.co/google/gemma-1.1-7b-it/blob/main/tokenizer_config.json#L1509
"c4ai-command-r-plus-08-2024": "<|END_OF_TURN_TOKEN|>",
# https://huggingface.co/unsloth/Qwen2.5-72B-Instruct/blob/main/tokenizer_config.json
"Qwen2.5-72B-Instruct":"<|im_end|>",
# https://huggingface.co/unsloth/DeepSeek-R1-Distill-Qwen-32B/blob/main/tokenizer_config.json
"DeepSeek-R1-Distill-Qwen-32B":"<|end▁of▁sentence|>",
"DeepSeek-V3-0324":"<|end▁of▁sentence|>",
# "openchat-3.5": "<|end_of_turn|>",
# "command-r-plus": "<|END_OF_TURN_TOKEN|>",
}
TOKEN_LIMIT_MAP = {
"mixtral-8x7b": 32768,
"nous-mixtral-8x7b": 32768,
"mistral-7b": 32768,
"yi-1.5-34b": 4096,
"gemma-7b": 8192,
"Llama-3.3-70B-Instruct": 131072,
"c4ai-command-r-plus-08-2024":1000000000000000019884624838656,
"Qwen2.5-72B-Instruct":131072,
"DeepSeek-R1-Distill-Qwen-32B":131072,
"DeepSeek-V3-0324":131072,
# "openchat-3.5": 8192,
# "command-r-plus": 32768,
# "llama3-70b": 8192,
# "zephyr-141b": 2048,
# "gpt-3.5-turbo": 8192,
}
TOKEN_RESERVED = 20
# https://platform.openai.com/docs/api-reference/models/list
AVAILABLE_MODELS_DICTS = [
{
"id": "Llama-3.3-70B-Instruct",
"description": "[meta-llama/Llama-3.3-70B-Instruct]: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct",
"object": "model",
"created": 1700000000,
"owned_by": "meta-llama"
},
{
"id": "Qwen2.5-72B-Instruct",
"description": "[Qwen/Qwen2.5-72B-Instruct]: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct",
"object": "model",
"created": 1700000000,
"owned_by": "Qwen"
},
{
"id": "c4ai-command-r-plus-08-2024",
"description": "[CohereForAI/c4ai-command-r-plus-08-2024]: https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024",
"object": "model",
"created": 1700000000,
"owned_by": "CohereForAI"
},
{
"id": "DeepSeek-R1-Distill-Qwen-32B",
"description": "[deepseek-ai/DeepSeek-R1-Distill-Qwen-32B]: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
"object": "model",
"created": 1700000000,
"owned_by": "deepseek-ai"
},
{
"id": "DeepSeek-V3-0324",
"description": "[deepseek-ai/DeepSeek-V3-0324]: https://huggingface.co/deepseek-ai/DeepSeek-V3-0324",
"object": "model",
"created": 1700000000,
"owned_by": "deepseek-ai"
},
{
"id": "Llama-3.1-Nemotron-70B-Instruct-HF",
"description": "[nvidia/Llama-3.1-Nemotron-70B-Instruct-HF]: https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
"object": "model",
"created": 1700000000,
"owned_by": "nvidia"
},
{
"id": "QwQ-32B-Preview",
"description": "[Qwen/QwQ-32B-Preview]: https://huggingface.co/Qwen/QwQ-32B-Preview",
"object": "model",
"created": 1700000000,
"owned_by": "Qwen"
},
{
"id": "Qwen2.5-Coder-32B-Instruct",
"description": "[Qwen/Qwen2.5-Coder-32B-Instruct]: https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct",
"object": "model",
"created": 1700000000,
"owned_by": "Qwen"
},
{
"id": "Llama-3.2-11B-Vision-Instruct",
"description": "[meta-llama/Llama-3.2-11B-Vision-Instruct]: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct",
"object": "model",
"created": 1700000000,
"owned_by": "meta-llama"
},
{
"id": "Hermes-3-Llama-3.1-8B",
"description": "[NousResearch/Hermes-3-Llama-3.1-8B]: https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B",
"object": "model",
"created": 1700000000,
"owned_by": "NousResearch"
},
{
"id": "Mistral-Nemo-Instruct-2407",
"description": "[mistralai/Mistral-Nemo-Instruct-2407]: https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407",
"object": "model",
"created": 1700000000,
"owned_by": "mistralai"
},
{
"id": "Phi-3.5-mini-instruct",
"description": "[microsoft/Phi-3.5-mini-instruct]: https://huggingface.co/microsoft/Phi-3.5-mini-instruct",
"object": "model",
"created": 1700000000,
"owned_by": "microsoft"
},
{
"id": "mixtral-8x7b",
"description": "[mistralai/Mixtral-8x7B-Instruct-v0.1]: https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1",
"object": "model",
"created": 1700000000,
"owned_by": "mistralai"
},
]
'''
https://huggingface.co/chat/models
var links = document.querySelectorAll('div.relative a');
var mlist=[];
links.forEach(link=>{
mlist.push(link.href.split('https://huggingface.co/chat/models/')[1])
})
p_MODEL_MAP(mlist);
p_AVAILABLE_MODELS_DICTS(mlist);
function p_MODEL_MAP(mlist){
let d = {}
mlist.forEach(m=>{
d[m.split('/')[1]]=m
});
console.log(d)
return d
}
function p_AVAILABLE_MODELS_DICTS(mlist){
let d = []
mlist.forEach(m=>{
d.push({
"id": m.split('/')[1],
"description": `[${m}]: https://huggingface.co/${m}`,
"object": "model",
"created": 1700000000,
"owned_by": m.split('/')[0],
},)
});
console.log(d)
return d
}
'''