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(chart): add config checksum (#1738) 02db805 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