Text Generation
Transformers
Safetensors
Chinese
English
qwen3
qwen
scoring
grading
evaluation
llm-judge
conversational
text-generation-inference
Instructions to use blue-tundra-42/code_and_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use blue-tundra-42/code_and_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="blue-tundra-42/code_and_model") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("blue-tundra-42/code_and_model") model = AutoModelForCausalLM.from_pretrained("blue-tundra-42/code_and_model") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use blue-tundra-42/code_and_model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "blue-tundra-42/code_and_model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "blue-tundra-42/code_and_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/blue-tundra-42/code_and_model
- SGLang
How to use blue-tundra-42/code_and_model with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "blue-tundra-42/code_and_model" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "blue-tundra-42/code_and_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "blue-tundra-42/code_and_model" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "blue-tundra-42/code_and_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use blue-tundra-42/code_and_model with Docker Model Runner:
docker model run hf.co/blue-tundra-42/code_and_model
| import os | |
| import re | |
| import json | |
| from abc import ABC, abstractmethod | |
| from typing import List, Dict, Any, Optional | |
| from utils import EvaluationRecord | |
| class BaseDataset(ABC): | |
| def __init__(self, **kwargs): | |
| self.evaluation_records: List[EvaluationRecord] = [] | |
| self.kwargs = kwargs | |
| def __len__(self): | |
| return len(self.evaluation_records) | |
| def load_and_prepare(self): | |
| """ | |
| Load data and populate the self.evaluation_records list. | |
| Each element is an EvaluationRecord object. | |
| """ | |
| pass | |
| def build_message(self) -> dict: | |
| """ Prepare the request message for inference and the format is OpenAI Chat Message Format: | |
| {"role": "user", "content": [{"type": "text", "text":"xxx"}, {"type": "image", "image": "xx.png"}, {"type":"audio", "audio":"xx.mp3"}]} | |
| """ | |
| pass | |
| def build_score_message(self, record: EvaluationRecord) -> dict: | |
| """ Prepare the request message for scorer and the format is OpenAI Chat Message Format: | |
| {"role": "user", "content": [{"type": "text", "text":"xxx"}} | |
| """ | |
| pass | |
| def compute_score(self, record: EvaluationRecord) -> float: | |
| """ | |
| Compute score for a single completed record. | |
| :param record: An EvaluationRecord object with prediction filled. | |
| :return: Score (float). | |
| """ | |
| pass | |
| def compute_metrics(self) -> Dict[str, Any]: | |
| """Compute final aggregated metrics based on all records.""" | |
| pass | |
| def save_results(self, file_path: str): | |
| """Save detailed results and final scores.""" | |
| if not os.path.exists(os.path.dirname(file_path)): | |
| os.makedirs(os.path.dirname(file_path)) | |
| EvaluationRecord.save_records_to_json(self.evaluation_records, file_path) | |
| print(f"Results saved to {file_path}") | |
| def load_results(self, file_path: str): | |
| """Load data from JSON file into evaluation_records.""" | |
| if not os.path.exists(file_path): | |
| print(f"File {file_path} does not exist") | |
| return | |
| with open(file_path, 'r', encoding='utf-8') as f: | |
| data = json.load(f) | |
| self.evaluation_records = [] | |
| for item in data: | |
| record = EvaluationRecord( | |
| id=item['id'], | |
| question=item['question'], | |
| message=item['message'], | |
| answer=item['answer'], | |
| response=item.get('response'), | |
| request_status=item.get('request_status', 'pending'), | |
| score_response=item.get('score_response'), | |
| score_status=item.get('score_status', 'pending'), | |
| score=item.get('score'), | |
| extra_info=item.get('extra_info', {}) | |
| ) | |
| self.evaluation_records.append(record) | |
| print(f"Loaded {len(self.evaluation_records)} records from {file_path}") |