Spaces:
Sleeping
Sleeping
File size: 5,659 Bytes
6e0397b 11fa80d 6e0397b 11fa80d 6e0397b e05bbc9 11fa80d 6e0397b 11fa80d 6e0397b 11fa80d 6e0397b 11fa80d 6e0397b 11fa80d 6e0397b 11fa80d 6e0397b 11fa80d 6e0397b 11fa80d 6e0397b 11fa80d 6e0397b 11fa80d 6e0397b 11fa80d 6e0397b 11fa80d 6e0397b 11fa80d 6e0397b 11fa80d 6e0397b 11fa80d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 |
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
from huggingface_hub import snapshot_download
from safetensors.torch import load_file
class ModelInput(BaseModel):
prompt: str
max_new_tokens: int = 50
app = FastAPI()
# Define model paths
base_model_path = "HuggingFaceTB/SmolLM2-135M-Instruct"
adapter_path = "khurrameycon/SmolLM-135M-Instruct-qa_pairs_converted.json-25epochs"
try:
# First load the base model
print("Loading base model...")
model = AutoModelForCausalLM.from_pretrained(
base_model_path,
torch_dtype=torch.float16,
trust_remote_code=True,
device_map="auto"
)
# Load tokenizer from base model
print("Loading tokenizer...")
tokenizer = AutoTokenizer.from_pretrained(base_model_path)
# Download adapter weights
print("Downloading adapter weights...")
adapter_path_local = snapshot_download(adapter_path)
# Load the safetensors file
print("Loading adapter weights...")
state_dict = load_file(f"{adapter_path_local}/adapter_model.safetensors")
# Load state dict into model
model.load_state_dict(state_dict, strict=False)
print("Model and adapter loaded successfully!")
except Exception as e:
print(f"Error during model loading: {e}")
raise
def generate_response(model, tokenizer, instruction, max_new_tokens=128):
"""Generate a response from the model based on an instruction."""
try:
messages = [{"role": "user", "content": instruction}]
input_text = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
inputs = tokenizer.encode(input_text, return_tensors="pt").to(model.device)
outputs = model.generate(
inputs,
max_new_tokens=max_new_tokens,
temperature=0.2,
top_p=0.9,
do_sample=True,
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
return response
except Exception as e:
raise ValueError(f"Error generating response: {e}")
@app.post("/generate")
async def generate_text(input: ModelInput):
try:
response = generate_response(
model=model,
tokenizer=tokenizer,
instruction=input.prompt,
max_new_tokens=input.max_new_tokens
)
return {"generated_text": response}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
@app.get("/")
async def root():
return {"message": "Welcome to the Model API!"}
# //////////////////////////////////////////
# from fastapi import FastAPI, HTTPException
# from pydantic import BaseModel
# from transformers import AutoModelForCausalLM, AutoTokenizer
# import torch
# from huggingface_hub import snapshot_download
# from safetensors.torch import load_file
# class ModelInput(BaseModel):
# prompt: str
# max_new_tokens: int = 2048
# app = FastAPI()
# # Define model paths
# base_model_path = "HuggingFaceTB/SmolLM2-135M-Instruct"
# adapter_path = "khurrameycon/SmolLM-135M-Instruct-qa_pairs_converted.json-25epochs"
# try:
# # Load the base model
# print("Loading base model...")
# model = AutoModelForCausalLM.from_pretrained(
# base_model_path,
# torch_dtype=torch.float16,
# device_map="cpu", # Explicitly set CPU
# # load_in_8bit=True # Enable int8 quantization
# trust_remote_code=True,
# # device_map="auto"
# )
# # Load tokenizer
# print("Loading tokenizer...")
# tokenizer = AutoTokenizer.from_pretrained(base_model_path)
# # Download adapter weights
# print("Downloading adapter weights...")
# adapter_path_local = snapshot_download(repo_id=adapter_path)
# # Load the safetensors file
# print("Loading adapter weights...")
# adapter_file = f"{adapter_path_local}/adapter_model.safetensors"
# state_dict = load_file(adapter_file)
# # Load state dict into model
# print("Applying adapter weights...")
# model.load_state_dict(state_dict, strict=False)
# print("Model and adapter loaded successfully!")
# except Exception as e:
# print(f"Error during model loading: {e}")
# raise
# def generate_response(model, tokenizer, instruction, max_new_tokens=2048):
# """Generate a response from the model based on an instruction."""
# try:
# # Format input for the model
# inputs = tokenizer.encode(instruction, return_tensors="pt").to(model.device)
# # Generate response
# outputs = model.generate(
# inputs,
# max_new_tokens=max_new_tokens,
# temperature=0.7,
# top_p=0.9,
# do_sample=True,
# )
# # Decode and return the output
# response = tokenizer.decode(outputs[0], skip_special_tokens=True)
# return response
# except Exception as e:
# raise ValueError(f"Error generating response: {e}")
# @app.post("/generate")
# async def generate_text(input: ModelInput):
# try:
# response = generate_response(
# model=model,
# tokenizer=tokenizer,
# instruction=input.prompt,
# max_new_tokens=2048
# )
# return {"generated_text": response}
# except Exception as e:
# raise HTTPException(status_code=500, detail=str(e))
# @app.get("/")
# async def root():
# return {"message": "Welcome to the Model API!"}
|