Improve error handling and response parsing for HF API b2dcace
Sgridda commited on
Spaces:
Sleeping
Sleeping
Commit History
Fix HF API integration - use GPT-2 model be491ce
Sgridda commited on
env varaible e4936f3
Sgridda commited on
added inferernce b64e7a0
Sgridda commited on
udpated 5f40b94
Sgridda commited on
updated 2588618
Sgridda commited on
modified 733f0e1
Sgridda commited on
trying different model a1f54c5
Sgridda commited on
trying lightweight model 487d58e
Sgridda commited on
renamed f4aa3fa
Sgridda commited on
made it simple d1e0f9b
Sgridda commited on
udpated message response 8eb5cff
Sgridda commited on
updated model config and added logs 4eca884
Sgridda commited on
Remove top_p parameter to clear warning 798c1c2
Sgridda commited on
Re-enable TinyLlama model for actual inference 39b69d9
Sgridda commited on
Convert to test server to isolate routing issue 9d8ec9c
Sgridda commited on
Switch to TinyLlama model to fit memory constraints 8a1669f
Sgridda commited on
Fix quantization for CPU by using BitsAndBytesConfig 8e65098
Sgridda commited on
Initial commit 937b2c0
Sgridda commited on