fix(hchat): config cleanup & fixes

huggingface · Oct 22, 2024 · 96ccc06 · 96ccc06
1 parent 70dbcda
commit 96ccc06
Showing 1 changed file with 7 additions and 12 deletions.
diff --git a/chart/env/prod.yaml b/chart/env/prod.yaml
@@ -45,10 +45,7 @@ envVars:
       {
         "name": "meta-llama/Meta-Llama-3.1-70B-Instruct",
         "id": "meta-llama/Meta-Llama-3.1-70B-Instruct",
-        "tokenizer": {
-          "tokenizerUrl": "https://huggingface.co/nsarrazin/llama3.1-tokenizer/resolve/main/tokenizer.json",
-          "tokenizerConfigUrl": "https://huggingface.co/nsarrazin/llama3.1-tokenizer/raw/main/tokenizer_config.json"
-        },
+        "tokenizer": "nsarrazin/llama3.1-tokenizer",
         "description": "Ideal for everyday use. A fast and extremely capable model matching closed source models' capabilities.",
         "modelUrl": "https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct",
         "websiteUrl": "https://llama.meta.com/",
@@ -78,10 +75,7 @@ envVars:
       },
       {
         "name": "CohereForAI/c4ai-command-r-plus-08-2024",
-        "tokenizer": {
-          "tokenizerUrl": "https://huggingface.co/nsarrazin/c4ai-command-r-v01-tokenizer/resolve/main/tokenizer.json",
-          "tokenizerConfigUrl": "https://huggingface.co/nsarrazin/c4ai-command-r-v01-tokenizer/raw/main/tokenizer_config.json"
-        },
+        "tokenizer": "nsarrazin/c4ai-command-r-v01-tokenizer",
         "description": "Cohere's largest language model, optimized for conversational interaction and tool use. Now with the 2024 update!",
         "modelUrl": "https://huggingface.co/CohereForAI/c4ai-command-r-plus-08-2024",
         "websiteUrl": "https://docs.cohere.com/docs/command-r-plus",
@@ -139,6 +133,7 @@ envVars:
       },
       {
         "name": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
+        "tokenizer": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
         "modelUrl": "https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
         "websiteUrl": "https://www.nvidia.com/",
         "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/nvidia-logo.png",
@@ -163,10 +158,10 @@ envVars:
             "prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters."
           }
         ],
-        "endpoint": {
+        "endpoints": [{
           "type": "openai",
           "baseURL": "https://api-inference.huggingface.co/models/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF/v1"
-        }
+        }]
       },
       {
         "name": "meta-llama/Llama-3.2-11B-Vision-Instruct",
@@ -180,7 +175,7 @@ envVars:
           "truncate": 14336,
           "max_new_tokens": 1536
         },
-        "endpoint": {
+        "endpoints": [{
           "type": "openai",
           "baseURL": "https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-11B-Vision-Instruct/v1",
           "multimodal": {
@@ -192,7 +187,7 @@ envVars:
               "preferredMimeType": "image/webp"
             }
           }
-        }
+        }]
       },
       {
         "name": "NousResearch/Hermes-3-Llama-3.1-8B",