Modelpublic

RichardErkhov/Nels2_-_SmolLM2-FT-SQL-Context-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes543downloads

Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

SmolLM2-FT-SQL-Context - GGUF

—Model creator: https://huggingface.co/Nels2/
—Original model: https://huggingface.co/Nels2/SmolLM2-FT-SQL-Context/

Name	Quant method	Size
SmolLM2-FT-SQL-Context.Q2_K.gguf	Q2_K	0.08GB
SmolLM2-FT-SQL-Context.IQ3_XS.gguf	IQ3_XS	0.08GB
SmolLM2-FT-SQL-Context.IQ3_S.gguf	IQ3_S	0.08GB
SmolLM2-FT-SQL-Context.Q3_K_S.gguf	Q3KS	0.08GB
SmolLM2-FT-SQL-Context.IQ3_M.gguf	IQ3_M	0.08GB
SmolLM2-FT-SQL-Context.Q3_K.gguf	Q3_K	0.09GB
SmolLM2-FT-SQL-Context.Q3_K_M.gguf	Q3KM	0.09GB
SmolLM2-FT-SQL-Context.Q3_K_L.gguf	Q3KL	0.09GB
SmolLM2-FT-SQL-Context.IQ4_XS.gguf	IQ4_XS	0.09GB
SmolLM2-FT-SQL-Context.Q4_0.gguf	Q4_0	0.09GB
SmolLM2-FT-SQL-Context.IQ4_NL.gguf	IQ4_NL	0.09GB
SmolLM2-FT-SQL-Context.Q4_K_S.gguf	Q4KS	0.1GB
SmolLM2-FT-SQL-Context.Q4_K.gguf	Q4_K	0.1GB
SmolLM2-FT-SQL-Context.Q4_K_M.gguf	Q4KM	0.1GB
SmolLM2-FT-SQL-Context.Q4_1.gguf	Q4_1	0.09GB
SmolLM2-FT-SQL-Context.Q5_0.gguf	Q5_0	0.1GB
SmolLM2-FT-SQL-Context.Q5_K_S.gguf	Q5KS	0.1GB
SmolLM2-FT-SQL-Context.Q5_K.gguf	Q5_K	0.1GB
SmolLM2-FT-SQL-Context.Q5_K_M.gguf	Q5KM	0.1GB
SmolLM2-FT-SQL-Context.Q5_1.gguf	Q5_1	0.1GB
SmolLM2-FT-SQL-Context.Q6_K.gguf	Q6_K	0.13GB
SmolLM2-FT-SQL-Context.Q8_0.gguf	Q8_0	0.13GB

Original model description: --- basemodel: HuggingFaceTB/SmolLM2-135M libraryname: transformers model_name: SmolLM2-FT-SQL-Context tags:

—generatedfromtrainer
—smol-course
—module_1
—trl
—sft licence: license ---

Model Card for SmolLM2-FT-SQL-Context

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

Quick start

python

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="Nels2/SmolLM2-FT-SQL-Context", 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:

bibtex

@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}}
}