Spaces:
Running
Running
Commit History
-
Add Cerebras, Silicon Flow, and Groq providers with debug logging.
- Added Groq provider with model ID mapping - Added debug logging to trace API key and model issues - Silicon Flow base URL changed from .cn to .com - Cerebras rate limits increased to 300/80 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>db83b53
-
$(cat <<EOF
Fix Groq and Cerebras model IDs and rate limits. Groq: Model IDs need inner prefixes (qwen/qwen3-32b not qwen3-32b) Cerebras: Removed inaccessible models, set higher rate limits Silicon: Increased rate limits to 300/min All providers now have appropriate concurrency and rate limit settings. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> EOF )332dd16 -
$(cat <<EOF
Update Cerebras model list based on API test results. Cerebras key only has access to llama3.1-8b currently. qwen-3-235b-a22b-instruct-2507 exists but is rate-limited. zai-glm-4.7 and gpt-oss-120b are not accessible with this key. Also added all models to CEREBRAS_MODEL_MAP for flexibility. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> EOF )0ba585f -
$(cat <<EOF
Fix model ID format for Cerebras and Silicon Flow providers. Cerebras API expects bare model IDs (e.g. "qwen-3-235b-a22b-instruct-2507") not the full "provider/model" format. Strip cerebras/ prefix before sending. Silicon Flow API similarly expects bare model IDs. Strip silicon/ prefix. Also updated REQUESTED_PROVIDER_MODELS and MODEL_CAPABILITIES to use correct ref format (cerebras/qwen-3-235b-a22b-instruct-2507, etc.). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> EOF )58a3721 -
Add Cerebras and Silicon Flow provider support
- Cerebras: qwen/qwen-3-235b-a22b-instruct-2507 (Qwen 3 235B) - Silicon Flow: Qwen3.6-35B/27B, Qwen3.5-35B/27B (VLM multimodal), Gemma-4-26B/31B reasoning models - Both use OpenAI-compatible /chat/completions via OpenAIChatTransport - API keys: CEREBRAS_API_KEY, SILICON_API_KEY Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>43ea069