phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

(feat) model context window.json add ollama/mistral, ollama/codellama, ollama/orca-mini, ollama/vicuna

Browse source
This commit is contained in:
ishaan-jaff 2023-11-02 09:18:26 -07:00
parent 6b7b66aa96
commit d09486f93b
1 changed files with 28 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

28
model_prices_and_context_window.json
View file

@ -579,6 +579,34 @@
"litellm_provider": "ollama", "litellm_provider": "ollama",
"mode": "completion" "mode": "completion"
}, },
"ollama/mistral": {
"max_tokens": 8192,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "ollama",
"mode": "completion"
},
"ollama/codellama": {
"max_tokens": 4096,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "ollama",
"mode": "completion"
},
"ollama/orca-mini": {
"max_tokens": 4096,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "ollama",
"mode": "completion"
},
"ollama/vicuna": {
"max_tokens": 2048,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "ollama",
"mode": "completion"
},
"deepinfra/meta-llama/Llama-2-70b-chat-hf": { "deepinfra/meta-llama/Llama-2-70b-chat-hf": {
"max_tokens": 4096, "max_tokens": 4096,
"input_cost_per_token": 0.000000700, "input_cost_per_token": 0.000000700,