Spaces:
Sleeping
Sleeping
File size: 4,234 Bytes
f5aec1b 0acb761 f5aec1b cc7d9c8 4d1e184 0acb761 bf0dc2a 0acb761 bf0dc2a 0acb761 60613b8 0acb761 60613b8 bf96358 f5aec1b 60613b8 |
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 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 |
model_list:
- model_name: hf-mistral-7b-instruct-v03
litellm_params:
model: huggingface/mistralai/Mistral-7B-Instruct-v0.3
api_key: os.environ/HUGGINGFACE_API_KEY
- model_name: hf-llama3-8b-instruct
litellm_params:
model: huggingface/meta-llama/Meta-Llama-3-8B-Instruct
api_key: os.environ/HUGGINGFACE_API_KEY
- model_name: awan-llama3-8b
litellm_params:
model: openai/Meta-Llama-3-8B-Instruct
api_key: os.environ/OTHER_AWANLLM_API_KEY
api_base: https://api.awanllm.com/v1
rpm: 10
- model_name: awan-mistral-7b-instruct-v03
litellm_params:
model: openai/Mistral-7B-Instruct
api_key: os.environ/OTHER_AWANLLM_API_KEY
api_base: https://api.awanllm.com/v1
rpm: 10
- model_name: groq-llama3-70b
litellm_params:
model: openai/llama3-70b-8192
api_key: os.environ/GROQ_API_KEY
api_base: https://api.groq.com/openai/v1
rpm: 30
- model_name: groq-llama3-8b
litellm_params:
model: openai/llama3-8b-8192
api_key: os.environ/GROQ_API_KEY
api_base: https://api.groq.com/openai/v1
rpm: 30
- model_name: groq-mixtral-8x7b
litellm_params:
model: openai/mixtral-8x7b-32768
api_key: os.environ/GROQ_API_KEY
api_base: https://api.groq.com/openai/v1
rpm: 30
- model_name: or-llama3-8b
litellm_params:
model: openai/meta-llama/llama-3-8b-instruct:free
api_key: os.environ/OPENROUTER_API_KEY
api_base: https://openrouter.ai/api/v1
rpm: 6
- model_name: or-openchat-7b
litellm_params:
model: openai/openchat/openchat-7b:free
api_key: os.environ/OPENROUTER_API_KEY
api_base: https://openrouter.ai/api/v1
rpm: 6
- model_name: or-zephyr-7b-beta
litellm_params:
model: openai/huggingfaceh4/zephyr-7b-beta:free
api_key: os.environ/OPENROUTER_API_KEY
api_base: https://openrouter.ai/api/v1
rpm: 6
- model_name: or-nous-capybara-7b
litellm_params:
model: openai/nousresearch/nous-capybara-7b:free
api_key: os.environ/OPENROUTER_API_KEY
api_base: https://openrouter.ai/api/v1
rpm: 6
- model_name: or-mythomist-7b
litellm_params:
model: "openrouter/gryphe/mythomist-7b:free"
api_key: os.environ/OPENROUTER_API_KEY
#api_base: https://openrouter.ai/api/v1
rpm: 6
- model_name: or-phi3-medium-128k
litellm_params:
model: openai/microsoft/phi-3-medium-128k-instruct:free
api_key: os.environ/OPENROUTER_API_KEY
api_base: https://openrouter.ai/api/v1
rpm: 6
- model_name: or-mistral-7b-v01
litellm_params:
model: openai/mistralai/mistral-7b-instruct:free
api_key: os.environ/OPENROUTER_API_KEY
api_base: https://openrouter.ai/api/v1
rpm: 6
- model_name: cf-qwen1-5-7b
litellm_params:
model: cloudflare/@cf/qwen/qwen1.5-7b-chat-awq
api_key: os.environ/CLOUDFLARE_API_KEY
- model_name: cf-hermes-2-pro-mistral-7b
litellm_params:
model: cloudflare/@hf/nousresearch/hermes-2-pro-mistral-7b
api_key: os.environ/CLOUDFLARE_API_KEY
- model_name: cf-llama3-8b
litellm_params:
model: cloudflare/@cf/meta/llama-3-8b-instruct
api_key: os.environ/CLOUDFLARE_API_KEY
- model_name: cf-deepseek-coder-6-7b
litellm_params:
model: cloudflare/@hf/thebloke/deepseek-coder-6.7b-instruct-awq
api_key: os.environ/CLOUDFLARE_API_KEY
- model_name: cf-sqlcoder-7b-2
litellm_params:
model: cloudflare/@cf/defog/sqlcoder-7b-2
api_key: os.environ/CLOUDFLARE_API_KEY
- model_name: cf-mistral-7b-v02
litellm_params:
model: cloudflare/@hf/mistral/mistral-7b-instruct-v0.2
api_key: os.environ/CLOUDFLARE_API_KEY
- model_name: gemini-pro-vision
litellm_params:
model: gemini/gemini-pro-vision
rpm: 15
- model_name: gemini-1.5-flash
litellm_params:
model: gemini/gemini-1.5-flash
rpm: 15
- model_name: gemini-1.5-pro
litellm_params:
model: gemini/gemini-1.5-pro
rpm: 2
tpm: 32000
litellm_settings:
success_callback: ["langfuse"]
failure_callback: ["langfuse"]
num_retries: 3
request_timeout: 20
allowed_fails: 3
drop_params: true
|