| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748 |
- default_model = "Qwen/Qwen2.5-72B-Instruct"
- default_image_model = "black-forest-labs/FLUX.1-dev"
- image_models = [
- default_image_model,
- "black-forest-labs/FLUX.1-schnell",
- ]
- fallback_models = [
- default_model,
- 'meta-llama/Llama-3.3-70B-Instruct',
- 'CohereForAI/c4ai-command-r-plus-08-2024',
- 'deepseek-ai/DeepSeek-R1-Distill-Qwen-32B',
- 'Qwen/QwQ-32B-Preview',
- 'nvidia/Llama-3.1-Nemotron-70B-Instruct-HF',
- 'Qwen/Qwen2.5-Coder-32B-Instruct',
- 'meta-llama/Llama-3.2-11B-Vision-Instruct',
- 'mistralai/Mistral-Nemo-Instruct-2407',
- 'microsoft/Phi-3.5-mini-instruct',
- ] + image_models
- model_aliases = {
- ### Chat ###
- "qwen-2.5-72b": "Qwen/Qwen2.5-Coder-32B-Instruct",
- "llama-3.3-70b": "meta-llama/Llama-3.3-70B-Instruct",
- "command-r-plus": "CohereForAI/c4ai-command-r-plus-08-2024",
- "deepseek-r1": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
- "qwq-32b": "Qwen/QwQ-32B-Preview",
- "nemotron-70b": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
- "qwen-2.5-coder-32b": "Qwen/Qwen2.5-Coder-32B-Instruct",
- "llama-3.2-11b": "meta-llama/Llama-3.2-11B-Vision-Instruct",
- "mistral-nemo": "mistralai/Mistral-Nemo-Instruct-2407",
- "phi-3.5-mini": "microsoft/Phi-3.5-mini-instruct",
- ### Image ###
- "flux": "black-forest-labs/FLUX.1-dev",
- "flux-dev": "black-forest-labs/FLUX.1-dev",
- "flux-schnell": "black-forest-labs/FLUX.1-schnell",
- ### Used in other providers ###
- "qwen-2-vl-7b": "Qwen/Qwen2-VL-7B-Instruct",
- "gemma-2-27b": "google/gemma-2-27b-it",
- "qwen-2-72b": "Qwen/Qwen2-72B-Instruct",
- "qvq-72b": "Qwen/QVQ-72B-Preview",
- "sd-3.5": "stabilityai/stable-diffusion-3.5-large",
- }
- extra_models = [
- "meta-llama/Llama-3.2-11B-Vision-Instruct",
- "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
- "NousResearch/Hermes-3-Llama-3.1-8B",
- ]
- default_vision_model = "meta-llama/Llama-3.2-11B-Vision-Instruct"
- vision_models = [default_vision_model, "Qwen/Qwen2-VL-7B-Instruct"]
|
