Spaces:
Running
Running
File size: 4,118 Bytes
19ea30a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 |
PROVIDER_DISPLAY_NAMES = {
"openai": "OpenAI",
"azure_openai": "Azure OpenAI",
"anthropic": "Anthropic",
"deepseek": "DeepSeek",
"google": "Google",
"alibaba": "Alibaba",
"moonshot": "MoonShot",
"unbound": "Unbound AI",
"ibm": "IBM",
"grok": "Grok",
}
# Predefined model names for common providers
model_names = {
"anthropic": ["claude-3-5-sonnet-20241022", "claude-3-5-sonnet-20240620", "claude-3-opus-20240229"],
"openai": ["gpt-4o", "gpt-4", "gpt-3.5-turbo", "o3-mini"],
"deepseek": ["deepseek-chat", "deepseek-reasoner"],
"google": ["gemini-2.0-flash", "gemini-2.0-flash-thinking-exp", "gemini-1.5-flash-latest",
"gemini-1.5-flash-8b-latest", "gemini-2.0-flash-thinking-exp-01-21", "gemini-2.0-pro-exp-02-05",
"gemini-2.5-pro-preview-03-25", "gemini-2.5-flash-preview-04-17"],
"ollama": ["qwen2.5:7b", "qwen2.5:14b", "qwen2.5:32b", "qwen2.5-coder:14b", "qwen2.5-coder:32b", "llama2:7b",
"deepseek-r1:14b", "deepseek-r1:32b"],
"azure_openai": ["gpt-4o", "gpt-4", "gpt-3.5-turbo"],
"mistral": ["pixtral-large-latest", "mistral-large-latest", "mistral-small-latest", "ministral-8b-latest"],
"alibaba": ["qwen-plus", "qwen-max", "qwen-vl-max", "qwen-vl-plus", "qwen-turbo", "qwen-long"],
"moonshot": ["moonshot-v1-32k-vision-preview", "moonshot-v1-8k-vision-preview"],
"unbound": ["gemini-2.0-flash", "gpt-4o-mini", "gpt-4o", "gpt-4.5-preview"],
"grok": [
"grok-3",
"grok-3-fast",
"grok-3-mini",
"grok-3-mini-fast",
"grok-2-vision",
"grok-2-image",
"grok-2",
],
"siliconflow": [
"deepseek-ai/DeepSeek-R1",
"deepseek-ai/DeepSeek-V3",
"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
"deepseek-ai/DeepSeek-V2.5",
"deepseek-ai/deepseek-vl2",
"Qwen/Qwen2.5-72B-Instruct-128K",
"Qwen/Qwen2.5-72B-Instruct",
"Qwen/Qwen2.5-32B-Instruct",
"Qwen/Qwen2.5-14B-Instruct",
"Qwen/Qwen2.5-7B-Instruct",
"Qwen/Qwen2.5-Coder-32B-Instruct",
"Qwen/Qwen2.5-Coder-7B-Instruct",
"Qwen/Qwen2-7B-Instruct",
"Qwen/Qwen2-1.5B-Instruct",
"Qwen/QwQ-32B-Preview",
"Qwen/Qwen2-VL-72B-Instruct",
"Qwen/Qwen2.5-VL-32B-Instruct",
"Qwen/Qwen2.5-VL-72B-Instruct",
"TeleAI/TeleChat2",
"THUDM/glm-4-9b-chat",
"Vendor-A/Qwen/Qwen2.5-72B-Instruct",
"internlm/internlm2_5-7b-chat",
"internlm/internlm2_5-20b-chat",
"Pro/Qwen/Qwen2.5-7B-Instruct",
"Pro/Qwen/Qwen2-7B-Instruct",
"Pro/Qwen/Qwen2-1.5B-Instruct",
"Pro/THUDM/chatglm3-6b",
"Pro/THUDM/glm-4-9b-chat",
],
"ibm": ["ibm/granite-vision-3.1-2b-preview", "meta-llama/llama-4-maverick-17b-128e-instruct-fp8",
"meta-llama/llama-3-2-90b-vision-instruct"],
"modelscope":[
"Qwen/Qwen2.5-Coder-32B-Instruct",
"Qwen/Qwen2.5-Coder-14B-Instruct",
"Qwen/Qwen2.5-Coder-7B-Instruct",
"Qwen/Qwen2.5-72B-Instruct",
"Qwen/Qwen2.5-32B-Instruct",
"Qwen/Qwen2.5-14B-Instruct",
"Qwen/Qwen2.5-7B-Instruct",
"Qwen/QwQ-32B-Preview",
"Qwen/Qwen2.5-VL-3B-Instruct",
"Qwen/Qwen2.5-VL-7B-Instruct",
"Qwen/Qwen2.5-VL-32B-Instruct",
"Qwen/Qwen2.5-VL-72B-Instruct",
"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
"deepseek-ai/DeepSeek-R1",
"deepseek-ai/DeepSeek-V3",
"Qwen/Qwen3-1.7B",
"Qwen/Qwen3-4B",
"Qwen/Qwen3-8B",
"Qwen/Qwen3-14B",
"Qwen/Qwen3-30B-A3B",
"Qwen/Qwen3-32B",
"Qwen/Qwen3-235B-A22B",
],
}
|