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

llama 3

Browse source
This commit is contained in:
lucca 2024-06-13 21:24:07 -03:00
parent 4366b0e553
commit e09f220600
No known key found for this signature in database
GPG key ID: 4AD5F117F068DBC1
2 changed files with 36 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

18
litellm/model_prices_and_context_window_backup.json
View file

@ -3347,6 +3347,24 @@
"litellm_provider": "deepinfra", "litellm_provider": "deepinfra",
"mode": "chat" "mode": "chat"
}, },
"deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": {
"max_tokens": 8191,
"max_input_tokens": 8191,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000008,
"output_cost_per_token": 0.00000008,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/meta-llama/Meta-Llama-3-70B-Instruct": {
"max_tokens": 8191,
"max_input_tokens": 8191,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000059,
"output_cost_per_token": 0.00000079,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/01-ai/Yi-34B-200K": { "deepinfra/01-ai/Yi-34B-200K": {
"max_tokens": 4096, "max_tokens": 4096,
"max_input_tokens": 200000, "max_input_tokens": 200000,

18
model_prices_and_context_window.json
View file

@ -3347,6 +3347,24 @@
"litellm_provider": "deepinfra", "litellm_provider": "deepinfra",
"mode": "chat" "mode": "chat"
}, },
"deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": {
"max_tokens": 8191,
"max_input_tokens": 8191,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000008,
"output_cost_per_token": 0.00000008,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/meta-llama/Meta-Llama-3-70B-Instruct": {
"max_tokens": 8191,
"max_input_tokens": 8191,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000059,
"output_cost_per_token": 0.00000079,
"litellm_provider": "deepinfra",
"mode": "chat"
},
"deepinfra/01-ai/Yi-34B-200K": { "deepinfra/01-ai/Yi-34B-200K": {
"max_tokens": 4096, "max_tokens": 4096,
"max_input_tokens": 200000, "max_input_tokens": 200000,