Downloads · 30 days
174
12% of all-time downloads
RichardErkhov/bigheiniuJ_-_zephyr-7b-full-ut-sft-gguf
bigheiniuJ_-_zephyr-7b-full-ut-sft-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
174
12% of all-time downloads
All-time downloads
1.5K
Public
Repo size
82.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf95.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
zephyr-7b-full-ut-sft - GGUF
| Name | Quant method | Size |
|---|---|---|
| zephyr-7b-full-ut-sft.Q2_K.gguf | Q2_K | 2.53GB |
| zephyr-7b-full-ut-sft.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| zephyr-7b-full-ut-sft.IQ3_S.gguf | IQ3_S | 2.96GB |
| zephyr-7b-full-ut-sft.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| zephyr-7b-full-ut-sft.IQ3_M.gguf | IQ3_M | 3.06GB |
| zephyr-7b-full-ut-sft.Q3_K.gguf | Q3_K | 3.28GB |
| zephyr-7b-full-ut-sft.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| zephyr-7b-full-ut-sft.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| zephyr-7b-full-ut-sft.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| zephyr-7b-full-ut-sft.Q4_0.gguf | Q4_0 | 3.83GB |
| zephyr-7b-full-ut-sft.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| zephyr-7b-full-ut-sft.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| zephyr-7b-full-ut-sft.Q4_K.gguf | Q4_K | 4.07GB |
| zephyr-7b-full-ut-sft.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| zephyr-7b-full-ut-sft.Q4_1.gguf | Q4_1 | 4.24GB |
| zephyr-7b-full-ut-sft.Q5_0.gguf | Q5_0 | 4.65GB |
| zephyr-7b-full-ut-sft.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| zephyr-7b-full-ut-sft.Q5_K.gguf | Q5_K | 4.78GB |
| zephyr-7b-full-ut-sft.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| zephyr-7b-full-ut-sft.Q5_1.gguf | Q5_1 | 5.07GB |
| zephyr-7b-full-ut-sft.Q6_K.gguf | Q6_K | 5.53GB |
| zephyr-7b-full-ut-sft.Q8_0.gguf | Q8_0 | 7.17GB |
base_model: alignment-handbook/zephyr-7b-sft-full library_name: transformers model_name: zephyr-7b-full-ut-sft tags:
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full. It has been trained using TRL.
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="bigheiniuJ/zephyr-7b-full-ut-sft", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
This model was trained with SFT.
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}}
}