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

Added Ollama LLMs for LLaMa and Mistral

Browse source
This commit is contained in:
Kade Heckel 2024-05-09 12:06:51 +01:00
parent dde2e3249a
commit 256107c999
2 changed files with 19 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
litellm/utils.py
View file

@ -6620,7 +6620,7 @@ def get_max_tokens(model: str):
raise Exception()
except:
raise Exception(
"This model isn't mapped yet. Add it here - https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json"
f"Model {model} from provider {custom_llm_provider} isn't mapped yet. Add it here - https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json"
)

18
model_prices_and_context_window.json
View file

@ -2749,6 +2749,24 @@
"litellm_provider": "ollama",
"mode": "completion"
},
"ollama/llama3": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000010,
"output_cost_per_token": 0.00000010,
"litellm_provider": "ollama",
"mode": "chat"
},
"ollama/llama3:70b": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "ollama",
"mode": "chat"
},
"ollama/mistral": {
"max_tokens": 8192,
"max_input_tokens": 8192,