RichardErkhov/peaceAsh_-_smolcourse_chapter1-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

smolcourse_chapter1 - GGUF

• Model creator: https://huggingface.co/peaceAsh/
• Original model: https://huggingface.co/peaceAsh/smolcourse_chapter1/

Name	Quant method	Size
smolcourse_chapter1.Q2_K.gguf	Q2_K	0.08GB
smolcourse_chapter1.IQ3_XS.gguf	IQ3_XS	0.08GB
smolcourse_chapter1.IQ3_S.gguf	IQ3_S	0.08GB
smolcourse_chapter1.Q3_K_S.gguf	Q3_K_S	0.08GB
smolcourse_chapter1.IQ3_M.gguf	IQ3_M	0.08GB
smolcourse_chapter1.Q3_K.gguf	Q3_K	0.09GB
smolcourse_chapter1.Q3_K_M.gguf	Q3_K_M	0.09GB
smolcourse_chapter1.Q3_K_L.gguf	Q3_K_L	0.09GB
smolcourse_chapter1.IQ4_XS.gguf	IQ4_XS	0.09GB
smolcourse_chapter1.Q4_0.gguf	Q4_0	0.09GB
smolcourse_chapter1.IQ4_NL.gguf	IQ4_NL	0.09GB
smolcourse_chapter1.Q4_K_S.gguf	Q4_K_S	0.1GB
smolcourse_chapter1.Q4_K.gguf	Q4_K	0.1GB
smolcourse_chapter1.Q4_K_M.gguf	Q4_K_M	0.1GB
smolcourse_chapter1.Q4_1.gguf	Q4_1	0.09GB
smolcourse_chapter1.Q5_0.gguf	Q5_0	0.1GB
smolcourse_chapter1.Q5_K_S.gguf	Q5_K_S	0.1GB
smolcourse_chapter1.Q5_K.gguf	Q5_K	0.1GB
smolcourse_chapter1.Q5_K_M.gguf	Q5_K_M	0.1GB
smolcourse_chapter1.Q5_1.gguf	Q5_1	0.1GB
smolcourse_chapter1.Q6_K.gguf	Q6_K	0.13GB
smolcourse_chapter1.Q8_0.gguf	Q8_0	0.13GB

Original model description:

base_model: HuggingFaceTB/SmolLM2-135M library_name: transformers model_name: sft_output tags: - generated_from_trainer - trl - sft licence: license

Model Card for sft_output

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "Can you write a python function to add 2 numbers?"
generator = pipeline("text-generation", model="peaceAsh/smolcourse_chapter1", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

• TRL: 0.12.1
• Transformers: 4.46.3
• Pytorch: 2.5.1
• Datasets: 3.1.0
• Tokenizers: 0.20.3

Citations

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}}
}