💥 [Fix] slow tokenizer issue, and finish by stop_sequences
abbb658
unverified
Husnain
commited on
Spaces:
Running
Running
Commit History
⚡ [Enhance] Use nous-mixtral-8x7b as default model
61ebb7f
unverified
Husnain
commited on
⚡ [Enhance] Use nous-mixtral-8x7b as default model
03fe2ac
unverified
Husnain
commited on
⚡ [Enhance] Use nous-mixtral-8x7b as default model
e4d90a2
unverified
Husnain
commited on
⚡ [Enhance] Upgrade gemma-7b to 1.1
11d1015
unverified
Husnain
commited on
💎 [Feature] New model supported: command-r-plus (CohereForai/c4ai-com…
c2cffc4
unverified
Husnain
commited on
💎 [Feature] New model supported: zephyr-orpo-141b (HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1)
0d1bd09
unverified
Husnain
commited on
💎 [Feature] New model supported: command-r-plus (CohereForai/c4ai-com…
18ccd47
unverified
Husnain
commited on
💎 [Feature] New model supported: command-r-plus (CohereForai/c4ai-com…
31a6c9b
unverified
Husnain
commited on
💎 [Feature] New model supported: command-r-plus (CohereForai/c4ai-com…
e6912fc
unverified
Husnain
commited on
♻️ [Refactor] Rename gemma-7b-1.1 to gemma-1.1-7b
006ffdb
unverified
Husnain
commited on
Update message_composer.py
1169354
unverified
Husnain
commited on
💎 [Feature] Enable gpt-3.5 in chat_api
12125b6
unverified
Husnain
commited on
♻️ [Refactor] Use tclogger, and configure envs better
124af16
unverified
Husnain
commited on
💥 [Fix] Revert chat templates with mannual version as nous-mixtral-8x…
99c68b6
unverified
Husnain
commited on
HF-LLM-API
7f1e89a
unverified
Husnain
commited on
HF-LLM-API
e2a9bea
unverified
Husnain
commited on