Spaces:
Sleeping
Sleeping
File size: 2,529 Bytes
df054a5 00f689b 97601b1 00f689b 4d476fc 193fe95 c842401 d4224b1 df054a5 d4224b1 df054a5 fb46333 df054a5 c0e2830 |
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 |
model_list:
- model_name: Qwen3-235B-A22B
litellm_params:
model: huggingface/Qwen/Qwen3-235B-A22B
api_key: os.environ/HF_TOKEN # ensure you have `HF_TOKEN` in your .env
- model_name: Qwen2.5-72B-Instruct
litellm_params:
model: huggingface/Qwen/Qwen2.5-72B-Instruct
api_key: os.environ/HF_TOKEN # ensure you have `HF_TOKEN` in your .env
- model_name: DeepSeek-R1-Distill-Qwen-32B
litellm_params:
model: huggingface/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
api_key: os.environ/HF_TOKEN # ensure you have `HF_TOKEN` in your .env
- model_name: Qwen/QwQ-32B
litellm_params:
model: huggingface/Qwen/QwQ-32B
api_key: os.environ/HF_TOKEN # ensure you have `HF_TOKEN` in your .env
- model_name: Llama-3.3-70B-Instruct
litellm_params:
model: huggingface/meta-llama/Llama-3.3-70B-Instruct
api_key: os.environ/HF_TOKEN # ensure you have `HF_TOKEN` in your .env
- model_name: Qwen2.5-VL-32B-Instruct
litellm_params:
model: huggingface/Qwen/Qwen2.5-VL-32B-Instruct
api_key: os.environ/HF_TOKEN # ensure you have `HF_TOKEN` in your .env
- model_name: DeepSeek-R1-Distill-Llama-70B
litellm_params:
model: huggingface/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
api_key: os.environ/HF_TOKEN # ensure you have `HF_TOKEN` in your .env
- model_name: ollama-phi3.5-3.8b
litellm_params:
model: ollama/phi3.5:3.8b
api_base: https://zhengr-ollama.hf.space
# Model-specific parameters
#model: "huggingface/mistralai/Mistral-7B-Instruct-v0.1"
#api_base: "<your-api-base>"
#api_key: "<your-api-key>" # [OPTIONAL] for hf inference endpoints
#initial_prompt_value: "\n"
#roles: {"system":{"pre_message":"<|im_start|>system\n", "post_message":"<|im_end|>"}, "assistant":{"pre_message":"<|im_start|>assistant\n","post_message":"<|im_end|>"}, "user":{"pre_message":"<|im_start|>user\n","post_message":"<|im_end|>"}}
#final_prompt_value: "\n"
#bos_token: "<s>"
#eos_token: "</s>"
#max_tokens: 4096
litellm_settings: # module level litellm settings - https://github.com/BerriAI/litellm/blob/main/litellm/__init__.py
drop_params: True
general_settings:
#master_key: sk-1234 # [OPTIONAL] Only use this if you to require all calls to contain this key (Authorization: Bearer sk-1234)
#alerting: ["slack"] # [OPTIONAL] If you want Slack Alerts for Hanging LLM requests, Slow llm responses, Budget Alerts. Make sure to set `SLACK_WEBHOOK_URL` in your env |