Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
feat(hchat): add QwQ-32B to prod HuggingChat config (#1746)
Browse files- chart/env/prod.yaml +17 -14
chart/env/prod.yaml
CHANGED
|
@@ -197,23 +197,16 @@ envVars:
|
|
| 197 |
]
|
| 198 |
},
|
| 199 |
{
|
| 200 |
-
"name": "Qwen/QwQ-32B
|
| 201 |
"preprompt": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.",
|
| 202 |
-
"modelUrl": "https://huggingface.co/Qwen/QwQ-32B
|
| 203 |
-
"websiteUrl": "https://qwenlm.github.io/blog/qwq-32b
|
| 204 |
"logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png",
|
| 205 |
-
"description": "QwQ is
|
| 206 |
"reasoning": {
|
| 207 |
-
"type": "
|
| 208 |
-
|
| 209 |
-
|
| 210 |
-
"stop": ["<|im_end|>"],
|
| 211 |
-
"truncate": 12288,
|
| 212 |
-
"max_new_tokens": 4096,
|
| 213 |
-
"temperature": 0.7,
|
| 214 |
-
"top_k": 20,
|
| 215 |
-
"top_p": 0.8,
|
| 216 |
-
"repetition_penalty": 1.05
|
| 217 |
},
|
| 218 |
"promptExamples": [
|
| 219 |
{
|
|
@@ -228,6 +221,12 @@ envVars:
|
|
| 228 |
"title": "Measuring 6 liters",
|
| 229 |
"prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters."
|
| 230 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 231 |
]
|
| 232 |
},
|
| 233 |
{
|
|
@@ -433,6 +432,10 @@ envVars:
|
|
| 433 |
{
|
| 434 |
"name": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
| 435 |
"transferTo": "meta-llama/Llama-3.3-70B-Instruct"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 436 |
}
|
| 437 |
]
|
| 438 |
PUBLIC_ORIGIN: "https://huggingface.co"
|
|
|
|
| 197 |
]
|
| 198 |
},
|
| 199 |
{
|
| 200 |
+
"name": "Qwen/QwQ-32B",
|
| 201 |
"preprompt": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.",
|
| 202 |
+
"modelUrl": "https://huggingface.co/Qwen/QwQ-32B",
|
| 203 |
+
"websiteUrl": "https://qwenlm.github.io/blog/qwq-32b/",
|
| 204 |
"logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png",
|
| 205 |
+
"description": "QwQ is the latest reasoning model released by the Qwen team, approaching the capabilities of R1 in benchmarks.",
|
| 206 |
"reasoning": {
|
| 207 |
+
"type": "tokens",
|
| 208 |
+
"beginToken": "",
|
| 209 |
+
"endToken": "</think>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 210 |
},
|
| 211 |
"promptExamples": [
|
| 212 |
{
|
|
|
|
| 221 |
"title": "Measuring 6 liters",
|
| 222 |
"prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters."
|
| 223 |
}
|
| 224 |
+
],
|
| 225 |
+
"endpoints": [
|
| 226 |
+
{
|
| 227 |
+
"type": "openai",
|
| 228 |
+
"baseURL": "https://internal.api-inference.huggingface.co/models/Qwen/QwQ-32B/v1"
|
| 229 |
+
}
|
| 230 |
]
|
| 231 |
},
|
| 232 |
{
|
|
|
|
| 432 |
{
|
| 433 |
"name": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
| 434 |
"transferTo": "meta-llama/Llama-3.3-70B-Instruct"
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"name": "Qwen/QwQ-32B-Preview",
|
| 438 |
+
"transferTo": "Qwen/QwQ-32B"
|
| 439 |
}
|
| 440 |
]
|
| 441 |
PUBLIC_ORIGIN: "https://huggingface.co"
|