Spaces:
Running
Running
fix(hchat): config cleanup & fixes
Browse files- chart/env/prod.yaml +7 -12
chart/env/prod.yaml
CHANGED
@@ -45,10 +45,7 @@ envVars:
|
|
45 |
{
|
46 |
"name": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
47 |
"id": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
48 |
-
"tokenizer":
|
49 |
-
"tokenizerUrl": "https://huggingface.co/nsarrazin/llama3.1-tokenizer/resolve/main/tokenizer.json",
|
50 |
-
"tokenizerConfigUrl": "https://huggingface.co/nsarrazin/llama3.1-tokenizer/raw/main/tokenizer_config.json"
|
51 |
-
},
|
52 |
"description": "Ideal for everyday use. A fast and extremely capable model matching closed source models' capabilities.",
|
53 |
"modelUrl": "https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct",
|
54 |
"websiteUrl": "https://llama.meta.com/",
|
@@ -78,10 +75,7 @@ envVars:
|
|
78 |
},
|
79 |
{
|
80 |
"name": "CohereForAI/c4ai-command-r-plus-08-2024",
|
81 |
-
"tokenizer":
|
82 |
-
"tokenizerUrl": "https://huggingface.co/nsarrazin/c4ai-command-r-v01-tokenizer/resolve/main/tokenizer.json",
|
83 |
-
"tokenizerConfigUrl": "https://huggingface.co/nsarrazin/c4ai-command-r-v01-tokenizer/raw/main/tokenizer_config.json"
|
84 |
-
},
|
85 |
"description": "Cohere's largest language model, optimized for conversational interaction and tool use. Now with the 2024 update!",
|
86 |
"modelUrl": "https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024",
|
87 |
"websiteUrl": "https://docs.cohere.com/docs/command-r-plus",
|
@@ -139,6 +133,7 @@ envVars:
|
|
139 |
},
|
140 |
{
|
141 |
"name": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
|
|
|
142 |
"modelUrl": "https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
|
143 |
"websiteUrl": "https://www.nvidia.com/",
|
144 |
"logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/nvidia-logo.png",
|
@@ -163,10 +158,10 @@ envVars:
|
|
163 |
"prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters."
|
164 |
}
|
165 |
],
|
166 |
-
"
|
167 |
"type": "openai",
|
168 |
"baseURL": "https://api-inference.huggingface.co/models/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF/v1"
|
169 |
-
}
|
170 |
},
|
171 |
{
|
172 |
"name": "meta-llama/Llama-3.2-11B-Vision-Instruct",
|
@@ -180,7 +175,7 @@ envVars:
|
|
180 |
"truncate": 14336,
|
181 |
"max_new_tokens": 1536
|
182 |
},
|
183 |
-
"
|
184 |
"type": "openai",
|
185 |
"baseURL": "https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-11B-Vision-Instruct/v1",
|
186 |
"multimodal": {
|
@@ -192,7 +187,7 @@ envVars:
|
|
192 |
"preferredMimeType": "image/webp"
|
193 |
}
|
194 |
}
|
195 |
-
}
|
196 |
},
|
197 |
{
|
198 |
"name": "NousResearch/Hermes-3-Llama-3.1-8B",
|
|
|
45 |
{
|
46 |
"name": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
47 |
"id": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
48 |
+
"tokenizer": "nsarrazin/llama3.1-tokenizer",
|
|
|
|
|
|
|
49 |
"description": "Ideal for everyday use. A fast and extremely capable model matching closed source models' capabilities.",
|
50 |
"modelUrl": "https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct",
|
51 |
"websiteUrl": "https://llama.meta.com/",
|
|
|
75 |
},
|
76 |
{
|
77 |
"name": "CohereForAI/c4ai-command-r-plus-08-2024",
|
78 |
+
"tokenizer": "nsarrazin/c4ai-command-r-v01-tokenizer",
|
|
|
|
|
|
|
79 |
"description": "Cohere's largest language model, optimized for conversational interaction and tool use. Now with the 2024 update!",
|
80 |
"modelUrl": "https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024",
|
81 |
"websiteUrl": "https://docs.cohere.com/docs/command-r-plus",
|
|
|
133 |
},
|
134 |
{
|
135 |
"name": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
|
136 |
+
"tokenizer": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
|
137 |
"modelUrl": "https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
|
138 |
"websiteUrl": "https://www.nvidia.com/",
|
139 |
"logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/nvidia-logo.png",
|
|
|
158 |
"prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters."
|
159 |
}
|
160 |
],
|
161 |
+
"endpoints": [{
|
162 |
"type": "openai",
|
163 |
"baseURL": "https://api-inference.huggingface.co/models/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF/v1"
|
164 |
+
}]
|
165 |
},
|
166 |
{
|
167 |
"name": "meta-llama/Llama-3.2-11B-Vision-Instruct",
|
|
|
175 |
"truncate": 14336,
|
176 |
"max_new_tokens": 1536
|
177 |
},
|
178 |
+
"endpoints": [{
|
179 |
"type": "openai",
|
180 |
"baseURL": "https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-11B-Vision-Instruct/v1",
|
181 |
"multimodal": {
|
|
|
187 |
"preferredMimeType": "image/webp"
|
188 |
}
|
189 |
}
|
190 |
+
}]
|
191 |
},
|
192 |
{
|
193 |
"name": "NousResearch/Hermes-3-Llama-3.1-8B",
|