Skip to content

Commit

Permalink
fix: put r1 model higher in list
Browse files Browse the repository at this point in the history
  • Loading branch information
nsarrazin committed Jan 21, 2025
1 parent 7793e4f commit b5e509e
Showing 1 changed file with 30 additions and 30 deletions.
60 changes: 30 additions & 30 deletions chart/env/prod.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -136,23 +136,15 @@ envVars:
]
},
{
"name": "Qwen/QwQ-32B-Preview",
"preprompt": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.",
"modelUrl": "https://huggingface.co/Qwen/QwQ-32B-Preview",
"websiteUrl": "https://qwenlm.github.io/blog/qwq-32b-preview/",
"logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png",
"description": "QwQ is an experiment model from the Qwen Team with advanced reasoning capabilities.",
"name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
"modelUrl": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
"websiteUrl": "https://deepseek.com/",
"logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/deepseek-logo.png",
"description": "The first reasoning model from DeepSeek, distilled into a 32B dense model. Outperforms o1-mini on multiple benchmarks.",
"reasoning": {
"type": "summarize"
},
"parameters": {
"stop": ["<|im_end|>"],
"truncate": 12288,
"max_new_tokens": 4096,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"repetition_penalty": 1.05
"type": "tokens",
"beginToken": "<think>",
"endToken": "</think>"
},
"promptExamples": [
{
Expand All @@ -167,6 +159,12 @@ envVars:
"title": "Measuring 6 liters",
"prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters."
}
],
"endpoints": [
{
"type": "openai",
"baseURL": "https://api-inference.huggingface.co/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/v1"
}
]
},
{
Expand Down Expand Up @@ -204,15 +202,23 @@ envVars:
]
},
{
"name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
"modelUrl": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
"websiteUrl": "https://deepseek.com/",
"logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/deepseek-logo.png",
"description": "The first reasoning model from DeepSeek, distilled into a 32B dense model. Outperforms o1-mini on multiple benchmarks.",
"name": "Qwen/QwQ-32B-Preview",
"preprompt": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.",
"modelUrl": "https://huggingface.co/Qwen/QwQ-32B-Preview",
"websiteUrl": "https://qwenlm.github.io/blog/qwq-32b-preview/",
"logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png",
"description": "QwQ is an experiment model from the Qwen Team with advanced reasoning capabilities.",
"reasoning": {
"type": "tokens",
"beginToken": "<think>",
"endToken": "</think>"
"type": "summarize"
},
"parameters": {
"stop": ["<|im_end|>"],
"truncate": 12288,
"max_new_tokens": 4096,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"repetition_penalty": 1.05
},
"promptExamples": [
{
Expand All @@ -227,12 +233,6 @@ envVars:
"title": "Measuring 6 liters",
"prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters."
}
],
"endpoints": [
{
"type": "openai",
"baseURL": "https://api-inference.huggingface.co/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/v1"
}
]
},
{
Expand Down

0 comments on commit b5e509e

Please sign in to comment.