RichardErkhov/Lekhansh_-_llama_3.2_1b_sft_merged_unsloth-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama_3.2_1b_sft_merged_unsloth - GGUF

• Model creator: https://huggingface.co/Lekhansh/
• Original model: https://huggingface.co/Lekhansh/llama_3.2_1b_sft_merged_unsloth/

Name	Quant method	Size
llama_3.2_1b_sft_merged_unsloth.Q2_K.gguf	Q2_K	2.96GB
llama_3.2_1b_sft_merged_unsloth.Q3_K_S.gguf	Q3_K_S	3.41GB
llama_3.2_1b_sft_merged_unsloth.Q3_K.gguf	Q3_K	3.74GB
llama_3.2_1b_sft_merged_unsloth.Q3_K_M.gguf	Q3_K_M	3.74GB
llama_3.2_1b_sft_merged_unsloth.Q3_K_L.gguf	Q3_K_L	4.03GB
llama_3.2_1b_sft_merged_unsloth.IQ4_XS.gguf	IQ4_XS	4.18GB
llama_3.2_1b_sft_merged_unsloth.Q4_0.gguf	Q4_0	4.34GB
llama_3.2_1b_sft_merged_unsloth.IQ4_NL.gguf	IQ4_NL	4.38GB
llama_3.2_1b_sft_merged_unsloth.Q4_K_S.gguf	Q4_K_S	4.37GB
llama_3.2_1b_sft_merged_unsloth.Q4_K.gguf	Q4_K	4.58GB
llama_3.2_1b_sft_merged_unsloth.Q4_K_M.gguf	Q4_K_M	4.58GB
llama_3.2_1b_sft_merged_unsloth.Q4_1.gguf	Q4_1	4.78GB
llama_3.2_1b_sft_merged_unsloth.Q5_0.gguf	Q5_0	5.21GB
llama_3.2_1b_sft_merged_unsloth.Q5_K_S.gguf	Q5_K_S	5.21GB
llama_3.2_1b_sft_merged_unsloth.Q5_K.gguf	Q5_K	5.34GB
llama_3.2_1b_sft_merged_unsloth.Q5_K_M.gguf	Q5_K_M	5.34GB
llama_3.2_1b_sft_merged_unsloth.Q5_1.gguf	Q5_1	5.65GB
llama_3.2_1b_sft_merged_unsloth.Q6_K.gguf	Q6_K	6.14GB
llama_3.2_1b_sft_merged_unsloth.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - trl license: apache-2.0 language: - en

Uploaded model

• Developed by: Lekhansh
• License: apache-2.0
• Finetuned from model : unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit

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