rollback

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1,2 +0,0 @@
-node_modules
-cache

Dockerfile

@@ -0,0 +1,21 @@
+# Use the official Python slim image
+FROM python:3.8-slim
+
+# Set environment variable for Hugging Face cache
+ENV HF_HOME=/tmp/.huggingface
+
+# Working directory
+WORKDIR /app
+
+# Copy dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY . .
+
+# Expose the port FastAPI will run on
+EXPOSE 7860
+
+# Run the API
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,61 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from typing import List
+import torch
+
+app = FastAPI(title="Language Model API")
+
+# Model configuration
+CHECKPOINT = "HuggingFaceTB/SmolLM2-135M-Instruct"
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Initialize model and tokenizer
+try:
+    tokenizer = AutoTokenizer.from_pretrained(CHECKPOINT)
+    model = AutoModelForCausalLM.from_pretrained(CHECKPOINT).to(DEVICE)
+except Exception as e:
+    raise RuntimeError(f"Failed to load model: {str(e)}")
+
+class ChatMessage(BaseModel):
+    role: str
+    content: str
+
+class ChatRequest(BaseModel):
+    messages: List[ChatMessage]
+    max_new_tokens: int = 50
+    temperature: float = 0.2
+    top_p: float = 0.9
+
+@app.post("/generate")
+async def generate_response(request: ChatRequest):
+    try:
+        # Convert messages to the format expected by the model
+        messages = [{"role": msg.role, "content": msg.content} for msg in request.messages]
+        
+        # Prepare input
+        input_text = tokenizer.apply_chat_template(messages, tokenize=False)
+        inputs = tokenizer.encode(input_text, return_tensors="pt").to(DEVICE)
+        
+        # Generate response
+        outputs = model.generate(
+            inputs,
+            max_new_tokens=request.max_new_tokens,
+            temperature=request.temperature,
+            top_p=request.top_p,
+            do_sample=True
+        )
+        
+        # Decode and return response
+        response_text = tokenizer.decode(outputs[0])
+        
+        return {
+            "generated_text": response_text
+        }
+    
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=7860)

index.ts

@@ -1,46 +0,0 @@
-import { pipeline } from "@huggingface/transformers";
-
-function loadingBar(total: number, current: number, barLength = 20) {
-  const filled = Math.round((current / total) * barLength);
-  const empty = barLength - filled;
-
-  const bar = `[${"#".repeat(filled)}${" ".repeat(empty)}] ${Math.round(
-    (current / total) * 100
-  )}%`;
-  process.stdout.write("\r" + bar);
-}
-
-process.stdout.write("\n"); // Move
-
-async function run() {
-  // Load a pre-trained model and tokenizer
-  const pipe = await pipeline(
-    "text-generation",
-    "HuggingFaceTB/SmolLM2-135M-Instruct",
-    // "HuggingFaceTB/SmolLM2-360M-Instruct",
-    // "HuggingFaceTB/SmolLM2-1.7B-Instruct",
-    {
-      cache_dir: "./cache",
-      progress_callback: (progress: any) => {
-        loadingBar(progress.total, progress.loaded);
-      },
-    }
-  );
-
-  // Perform sentiment analysis
-  const result = await pipe(
-    [
-      {
-        role: "user",
-        content: `Recomend a song for me based on these songs: 'Dheere Dheere Aap Mere', 'Zara Zara - Deep House Mix', 'Hey Minnale (From "Amaran") (Tamil)', 'Apna Bana Le (From "Bhediya")`,
-      },
-    ],
-    {
-      max_new_tokens: 100,
-    }
-  );
-
-  console.log(result);
-}
-
-run().catch(console.error);

package.json

@@ -1,17 +0,0 @@
-{
-  "name": "test",
-  "version": "1.0.0",
-  "main": "index.js",
-  "scripts": {
-    "test": "echo \"Error: no test specified\" && exit 1"
-  },
-  "keywords": [],
-  "author": "",
-  "license": "ISC",
-  "type": "commonjs",
-  "description": "",
-  "dependencies": {
-    "@huggingface/transformers": "^3.3.1",
-    "@xenova/transformers": "^2.17.2"
-  }
-}

requirements.txt

@@ -0,0 +1,7 @@
+fastapi
+uvicorn
+transformers
+torch
+peft
+huggingface_hub
+safetensors