Hugging Face's logo

RichardErkhov
/
trl-lib_-_Qwen2-0.5B-KTO-gguf

GGUF
conversational
Model card Files
xet
 Community
How to use from
llama.cpp
Install from brew 
brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RichardErkhov/trl-lib_-_Qwen2-0.5B-KTO-gguf:
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/trl-lib_-_Qwen2-0.5B-KTO-gguf:
Install from WinGet (Windows) 
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RichardErkhov/trl-lib_-_Qwen2-0.5B-KTO-gguf:
# Run inference directly in the terminal:
llama-cli -hf RichardErkhov/trl-lib_-_Qwen2-0.5B-KTO-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 RichardErkhov/trl-lib_-_Qwen2-0.5B-KTO-gguf:
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/trl-lib_-_Qwen2-0.5B-KTO-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 RichardErkhov/trl-lib_-_Qwen2-0.5B-KTO-gguf:
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/trl-lib_-_Qwen2-0.5B-KTO-gguf:
Use Docker 
docker model run hf.co/RichardErkhov/trl-lib_-_Qwen2-0.5B-KTO-gguf:
Quick Links

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Qwen2-0.5B-KTO - GGUF

Name Quant method Size
Qwen2-0.5B-KTO.Q2_K.gguf Q2_K 0.32GB
Qwen2-0.5B-KTO.Q3_K_S.gguf Q3_K_S 0.32GB
Qwen2-0.5B-KTO.Q3_K.gguf Q3_K 0.33GB
Qwen2-0.5B-KTO.Q3_K_M.gguf Q3_K_M 0.33GB
Qwen2-0.5B-KTO.Q3_K_L.gguf Q3_K_L 0.34GB
Qwen2-0.5B-KTO.IQ4_XS.gguf IQ4_XS 0.33GB
Qwen2-0.5B-KTO.Q4_0.gguf Q4_0 0.33GB
Qwen2-0.5B-KTO.IQ4_NL.gguf IQ4_NL 0.33GB
Qwen2-0.5B-KTO.Q4_K_S.gguf Q4_K_S 0.36GB
Qwen2-0.5B-KTO.Q4_K.gguf Q4_K 0.37GB
Qwen2-0.5B-KTO.Q4_K_M.gguf Q4_K_M 0.37GB
Qwen2-0.5B-KTO.Q4_1.gguf Q4_1 0.35GB
Qwen2-0.5B-KTO.Q5_0.gguf Q5_0 0.37GB
Qwen2-0.5B-KTO.Q5_K_S.gguf Q5_K_S 0.38GB
Qwen2-0.5B-KTO.Q5_K.gguf Q5_K 0.39GB
Qwen2-0.5B-KTO.Q5_K_M.gguf Q5_K_M 0.39GB
Qwen2-0.5B-KTO.Q5_1.gguf Q5_1 0.39GB
Qwen2-0.5B-KTO.Q6_K.gguf Q6_K 0.47GB
Qwen2-0.5B-KTO.Q8_0.gguf Q8_0 0.49GB

Original model description:

base_model: Qwen/Qwen2-0.5B-Instruct datasets: trl-lib/kto-mix-14k library_name: transformers model_name: Qwen2-0.5B-KTO tags: - generated_from_trainer - trl - kto licence: license

Model Card for Qwen2-0.5B-KTO

This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct on the trl-lib/kto-mix-14k dataset. It has been trained using TRL.

Quick start 

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="qgallouedec/Qwen2-0.5B-KTO", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

Visualize in Weights & Biases

This model was trained with KTO, a method introduced in KTO: Model Alignment as Prospect Theoretic Optimization.

Framework versions

  • TRL: 0.12.0.dev0
  • Transformers: 4.46.0.dev0
  • Pytorch: 2.4.1
  • Datasets: 3.0.1
  • Tokenizers: 0.20.0

Citations

Cite KTO as:

@article{ethayarajh2024kto,
    title        = {{KTO: Model Alignment as Prospect Theoretic Optimization}},
    author       = {Kawin Ethayarajh and Winnie Xu and Niklas Muennighoff and Dan Jurafsky and Douwe Kiela},
    year         = 2024,
    eprint       = {arXiv:2402.01306},
}

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}
Downloads last month
56
GGUF
Model size
0.5B params
Architecture
qwen2
Hardware compatibility
Log In to add your hardware

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for RichardErkhov/trl-lib_-_Qwen2-0.5B-KTO-gguf