scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-06 08:16:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 79

Merge pull request #4730 from danielbichuetti/fireworks-fix-cost-map

Browse source 
[Feature]: Allow using custom and on-demand models in Fireworks AI + update data to model_prices_and_context_window.json
This commit is contained in:
Krish Dholakia 2024-07-27 16:43:48 -07:00 • committed by GitHub
commit 9efebc490d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 5 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
model_prices_and_context_window.json
View file

@ -4373,7 +4373,7 @@
"litellm_provider": "perplexity",
"mode": "chat"
},
"fireworks_ai/firefunction-v2": {
"fireworks_ai/accounts/fireworks/models/firefunction-v2": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
@ -4384,7 +4384,7 @@
"supports_function_calling": true,
"source": "https://fireworks.ai/pricing"
},
"fireworks_ai/mixtral-8x22b-instruct-hf": {
"fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": {
"max_tokens": 65536,
"max_input_tokens": 65536,
"max_output_tokens": 65536,
@ -4395,7 +4395,7 @@
"supports_function_calling": true,
"source": "https://fireworks.ai/pricing"
},
"fireworks_ai/qwen2-72b-instruct": {
"fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": {
"max_tokens": 32768,
"max_input_tokens": 32768,
"max_output_tokens": 32768,
@ -4406,7 +4406,7 @@
"supports_function_calling": true,
"source": "https://fireworks.ai/pricing"
},
"fireworks_ai/yi-large": {
"fireworks_ai/accounts/fireworks/models/yi-large": {
"max_tokens": 32768,
"max_input_tokens": 32768,
"max_output_tokens": 32768,
@ -4417,7 +4417,7 @@
"supports_function_calling": true,
"source": "https://fireworks.ai/pricing"
},
"fireworks_ai/deepseek-coder-v2-instruct": {
"fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": {
"max_tokens": 65536,
"max_input_tokens": 65536,
"max_output_tokens": 8192,