ORPO: Monolithic Preference Optimization without Reference Model
Paper • 2403.07691 • Published • 72
How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Nxcode-CQ-7B-orpo-GGUF:# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Nxcode-CQ-7B-orpo-GGUF:Use pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf QuantFactory/Nxcode-CQ-7B-orpo-GGUF:# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/Nxcode-CQ-7B-orpo-GGUF:Build from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf QuantFactory/Nxcode-CQ-7B-orpo-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/Nxcode-CQ-7B-orpo-GGUF:Use Docker
docker model run hf.co/QuantFactory/Nxcode-CQ-7B-orpo-GGUF:Quick Links
QuantFactory/Nxcode-CQ-7B-orpo-GGUF
This is quantized version of NTQAI/Nxcode-CQ-7B-orpo created suing llama.cpp
Model Description
Nxcode-CQ-7B-orpo is an Monolithic Preference Optimization without Reference Model fine-tune of Qwen/CodeQwen1.5-7B on 100k samples of high-quality ranking data.
Evalplus
| EvalPlus | pass@1 |
|---|---|
| HumanEval | 86.6 |
| HumanEval+ | 83.5 |
| MBPP(v0.2.0) | 82.3 |
| MBPP+(v0.2.0) | 70.4 |
We use a simple template to generate the solution for evalplus:
"Complete the following Python function:\n{prompt}"
| Models | HumanEval | HumanEval+ |
|---|---|---|
| GPT-4-Turbo (April 2024) | 90.2 | 86.6 |
| GPT-4 (May 2023) | 88.4 | 81.17 |
| GPT-4-Turbo (Nov 2023) | 85.4 | 79.3 |
| CodeQwen1.5-7B-Chat | 83.5 | 78.7 |
| claude-3-opus (Mar 2024) | 82.9 | 76.8 |
| DeepSeek-Coder-33B-instruct | 81.1 | 75.0 |
| WizardCoder-33B-V1.1 | 79.9 | 73.2 |
| OpenCodeInterpreter-DS-33B | 79.3 | 73.8 |
| speechless-codellama-34B-v2.0 | 77.4 | 72 |
| GPT-3.5-Turbo (Nov 2023) | 76.8 | 70.7 |
| Llama3-70B-instruct | 76.2 | 70.7 |
Bigcode Leaderboard
09/05/2024
Top 1 average score.
Top 2 winrate.
Quickstart
Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents. You should upgrade the transformers if you receive an error when loading the tokenizer
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"NTQAI/Nxcode-CQ-7B-orpo",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("NTQAI/Nxcode-CQ-7B-orpo")
prompt = """Complete the following Python function:
from typing import List
def has_close_elements(numbers: List[float], threshold: float) -> bool:
""" Check if in given list of numbers, are any two numbers closer to each other than
given threshold.
>>> has_close_elements([1.0, 2.0, 3.0], 0.5)
False
>>> has_close_elements([1.0, 2.8, 3.0, 4.0, 5.0, 2.0], 0.3)
True
"""
"""
messages = [
{"role": "user", "content": prompt}
]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
res = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
- Downloads last month
- 144
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Model tree for QuantFactory/Nxcode-CQ-7B-orpo-GGUF
Base model
NTQAI/Nxcode-CQ-7B-orpo
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf QuantFactory/Nxcode-CQ-7B-orpo-GGUF:# Run inference directly in the terminal: llama-cli -hf QuantFactory/Nxcode-CQ-7B-orpo-GGUF: