Spaces:
Sleeping
Sleeping
Commit History
HuggingChat 2026 (#1875)
7bf1507
unverified
fix: reduce min pods following closure (#1865)
de0d97b
unverified
fix(infra): remove group order
7469079
unverified
chore: add internal (#1828)
244889b
unverified
Adrien
commited on
fix(hchat): `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` endpoint url
8d11e8e
New `InferenceClient` endpoint type (#1813)
4906f37
unverified
fix(cohere): 404 due to org rename (#1815)
51b7de0
unverified
fix(huggingchat): sed api-inference (#1814)
72dbfaf
unverified
oOraph
Raphael Glon
commited on
fix: correct typo in prompt example in prod.yaml
ee5dfa3
feat: update banner
28954fa
feat: new model 29-04-25 (#1808)
e390fd0
unverified
fix: config bits
7fbafc9
feat(huggingchat): update available models
bb8ac6e
feat: add Mistral-Small-3.1-24B-Instruct-2503 model and Phi-4 (#1806)
9111ea7
unverified
fix: prod config
29851bb
feat: rework example layout to work better on mobile
2335377
feat: allow storing env variable in DB (#1802)
48059af
unverified
feat: admin CLI login (#1789)
afbe0de
unverified
fix(hchat): update endpoint for qwq
c44d626
fix: add missing examples in prod config
8326cc3
fix: duplicate endpoints in task model
49c41c7
Revert "Revert "feat(config): add gemma 3 to prod config (#1753)""
9308560
feat: improve task model tool calling (#1755)
d37f9ca
unverified
Revert "feat(config): add gemma 3 to prod config (#1753)"
c7c1fe9
feat(config): add gemma 3 to prod config (#1753)
9828685
unverified
fix: improve tasks performance
28b6d44
feat(model): configure Llama-3.1-8B-Instruct with OpenAI-compatible endpoint
55ff303
feat(tasks): use tools for tasks if available (#1749)
6655689
unverified
feat(hchat): add QwQ-32B to prod HuggingChat config (#1746)
7139d72
unverified
fix(prod): model config
2b6c120
fix(huggingchat): add additional stop token for model configuration
a6bb678
fix(hchat): update internal endpoint (#1716)
54a5aad
unverified
refactor: remove deprecated EXPOSE_API environment variable
a06cb0c
fix: handle no beginToken for token based reasoning models (#1713)
a68038a
unverified
feat(hchat): move Llama 3.3 70B as the default model
eccf709
feat(chart): use inference proxy (#1688)
cf63293
unverified
Update prod.yaml
a11228d
unverified
Adrien
commited on