fix: remove exAI 6780118
imtrt004 commited on
Spaces:
Sleeping
Sleeping
Commit History
fix: chat error d5be08f
imtrt004 commited on
fix: chat error 1589f43
imtrt004 commited on
feat: update base free model 67a030a
imtrt004 commited on
fix: update limit 69975bb
imtrt004 commited on
fix: update context window and prompt 27128c4
imtrt004 commited on
feat: add cerebras api and super mode a488f5e
imtrt004 commited on
feat: answering question 4d4abe9
imtrt004 commited on
feat: line number and multi docs 391fc60
imtrt004 commited on
fix: improve chunking e2cc6a2
imtrt004 commited on
fix: llm model info e859e26
imtrt004 commited on
feat: add groq api and deepmind 29cfc16
imtrt004 commited on
perf: greedy decoding + dtype fix - 2-3x faster inference on CPU d16b829
imtrt004 commited on
feat: self-hosted Qwen2.5-1.5B-Instruct via transformers — no external API, no compilation deea70e
imtrt004 commited on
feat: replace llama-cpp-python/Groq with free HF InferenceClient (zero compilation) 98e3f05
imtrt004 commited on
Initial backend b5be2eb
imtrt004 commited on