mirror of
https://github.com/tiennm99/litellm.git
synced 2026-08-06 10:21:32 +00:00
Use sepecific llama2 and llama3 model names in Ollama
This commit is contained in:
@@ -3354,6 +3354,15 @@
|
||||
"litellm_provider": "ollama",
|
||||
"mode": "completion"
|
||||
},
|
||||
"ollama/llama2:7b": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
"max_output_tokens": 4096,
|
||||
"input_cost_per_token": 0.0,
|
||||
"output_cost_per_token": 0.0,
|
||||
"litellm_provider": "ollama",
|
||||
"mode": "completion"
|
||||
},
|
||||
"ollama/llama2:13b": {
|
||||
"max_tokens": 4096,
|
||||
"max_input_tokens": 4096,
|
||||
@@ -3390,6 +3399,15 @@
|
||||
"litellm_provider": "ollama",
|
||||
"mode": "chat"
|
||||
},
|
||||
"ollama/llama3:8b": {
|
||||
"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/llama3:70b": {
|
||||
"max_tokens": 8192,
|
||||
"max_input_tokens": 8192,
|
||||
|
||||
Reference in New Issue
Block a user