Upload folder using huggingface_hub

README.md

@@ -30,12 +30,12 @@ POST /v1/messages
 
 ### Example Request
 ```bash
-curl -X POST "https://YOUR_SPACE.hf.space/v1/messages" \
+curl -X POST "https://YOUR_SPACE.hf.space/anthropic/v1/messages" \
   -H "Content-Type: application/json" \
   -H "x-api-key: your-api-key" \
   -H "anthropic-version: 2023-06-01" \
   -d '{
-    "model": "smollm2-135m",
+    "model": "qwen2.5-coder-3b",
     "max_tokens": 256,
     "messages": [
       {"role": "user", "content": "Hello, how are you?"}
@@ -45,10 +45,10 @@ curl -X POST "https://YOUR_SPACE.hf.space/v1/messages" \
 
 ### Streaming Example
 ```bash
-curl -X POST "https://YOUR_SPACE.hf.space/v1/messages" \
+curl -X POST "https://YOUR_SPACE.hf.space/anthropic/v1/messages" \
   -H "Content-Type: application/json" \
   -d '{
-    "model": "smollm2-135m",
+    "model": "qwen2.5-coder-3b",
     "max_tokens": 256,
     "stream": true,
     "messages": [
@@ -65,11 +65,11 @@ import anthropic
 
 client = anthropic.Anthropic(
     api_key="any-key",
-    base_url="https://YOUR_SPACE.hf.space"
+    base_url="https://YOUR_SPACE.hf.space/anthropic"
 )
 
 message = client.messages.create(
-    model="smollm2-135m",
+    model="qwen2.5-coder-3b",
     max_tokens=256,
     messages=[{"role": "user", "content": "Hello!"}]
 )
@@ -82,11 +82,11 @@ import Anthropic from '@anthropic-ai/sdk';
 
 const client = new Anthropic({
   apiKey: 'any-key',
-  baseURL: 'https://YOUR_SPACE.hf.space'
+  baseURL: 'https://YOUR_SPACE.hf.space/anthropic'
 });
 
 const message = await client.messages.create({
-  model: 'smollm2-135m',
+  model: 'qwen2.5-coder-3b',
   max_tokens: 256,
   messages: [{ role: 'user', content: 'Hello!' }]
 });
@@ -95,10 +95,10 @@ console.log(message.content[0].text);
 
 ## Model Info
 
-- **Model**: HuggingFaceTB/SmolLM2-135M-Instruct
-- **Parameters**: 135 Million
-- **Optimized for**: CPU inference
-- **Context Length**: 2048 tokens
+- **Model**: Qwen/Qwen2.5-Coder-3B-Instruct
+- **Parameters**: 3 Billion
+- **Optimized for**: Code & Tool reasoning
+- **Context Length**: 32K tokens
 
 ## Rate Limits
 

app.py

@@ -57,7 +57,7 @@ logger.info(f"Log file: {LOG_FILE}")
 logger.info("=" * 60)
 
 # ============== Configuration ==============
-MODEL_ID = "HuggingFaceTB/SmolLM2-135M-Instruct"
+MODEL_ID = "Qwen/Qwen2.5-Coder-3B-Instruct"
 DEVICE = "cpu"
 
 model = None
@@ -474,7 +474,7 @@ async def health():
 async def openai_list_models():
     """List models (OpenAI format)"""
     return OpenAIModelList(
-        data=[OpenAIModel(id="smollm2-135m", created=int(time.time()), owned_by="huggingface")]
+        data=[OpenAIModel(id="qwen2.5-coder-3b", created=int(time.time()), owned_by="qwen")]
     )
 
 @app.post("/v1/chat/completions")
@@ -625,11 +625,11 @@ async def anthropic_list_models():
     return {
         "object": "list",
         "data": [{
-            "id": "smollm2-135m",
+            "id": "qwen2.5-coder-3b",
             "object": "model",
             "created": int(time.time()),
-            "owned_by": "huggingface",
-            "display_name": "SmolLM2 135M Instruct",
+            "owned_by": "qwen",
+            "display_name": "Qwen2.5 Coder 3B Instruct",
             "supports_thinking": True
         }]
     }