Modelpublic

RichardErkhov/Trelis_-_Llama-3.2-1B-Instruct-MATH-synthetic-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes849downloads

Model Card

Quantization made by Richard Erkhov.

Llama-3.2-1B-Instruct-MATH-synthetic - GGUF

—Model creator: https://huggingface.co/Trelis/
—Original model: https://huggingface.co/Trelis/Llama-3.2-1B-Instruct-MATH-synthetic/

Name	Quant method	Size
Llama-3.2-1B-Instruct-MATH-synthetic.Q2_K.gguf	Q2_K	0.54GB
Llama-3.2-1B-Instruct-MATH-synthetic.IQ3_XS.gguf	IQ3_XS	0.58GB
Llama-3.2-1B-Instruct-MATH-synthetic.IQ3_S.gguf	IQ3_S	0.6GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q3_K_S.gguf	Q3KS	0.6GB
Llama-3.2-1B-Instruct-MATH-synthetic.IQ3_M.gguf	IQ3_M	0.61GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q3_K.gguf	Q3_K	0.64GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q3_K_M.gguf	Q3KM	0.64GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q3_K_L.gguf	Q3KL	0.68GB
Llama-3.2-1B-Instruct-MATH-synthetic.IQ4_XS.gguf	IQ4_XS	0.7GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q4_0.gguf	Q4_0	0.72GB
Llama-3.2-1B-Instruct-MATH-synthetic.IQ4_NL.gguf	IQ4_NL	0.72GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q4_K_S.gguf	Q4KS	0.72GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q4_K.gguf	Q4_K	0.75GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q4_K_M.gguf	Q4KM	0.75GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q4_1.gguf	Q4_1	0.77GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q5_0.gguf	Q5_0	0.83GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q5_K_S.gguf	Q5KS	0.83GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q5_K.gguf	Q5_K	0.85GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q5_K_M.gguf	Q5KM	0.85GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q5_1.gguf	Q5_1	0.89GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q6_K.gguf	Q6_K	0.95GB
Llama-3.2-1B-Instruct-MATH-synthetic.Q8_0.gguf	Q8_0	1.23GB

Original model description: --- base_model: unsloth/Llama-3.2-1B-Instruct language:

Uploaded model

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.