Modelpublic

RichardErkhov/saqada_-_Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes718downloads

Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.2-3B-with-16bit-mergedloraadapters-MOV_v2 - GGUF

—Model creator: https://huggingface.co/saqada/
—Original model: https://huggingface.co/saqada/Llama-3.2-3B-with-16bit-mergedloraadapters-MOV_v2/

Name	Quant method	Size
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q2_K.gguf	Q2_K	1.27GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.IQ3_XS.gguf	IQ3_XS	1.38GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.IQ3_S.gguf	IQ3_S	1.44GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q3_K_S.gguf	Q3KS	1.44GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.IQ3_M.gguf	IQ3_M	1.49GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q3_K.gguf	Q3_K	1.57GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q3_K_M.gguf	Q3KM	1.57GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q3_K_L.gguf	Q3KL	1.69GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.IQ4_XS.gguf	IQ4_XS	1.71GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q4_0.gguf	Q4_0	1.79GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.IQ4_NL.gguf	IQ4_NL	1.79GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q4_K_S.gguf	Q4KS	1.8GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q4_K.gguf	Q4_K	1.88GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q4_K_M.gguf	Q4KM	1.88GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q4_1.gguf	Q4_1	1.95GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q5_0.gguf	Q5_0	2.11GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q5_K_S.gguf	Q5KS	2.11GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q5_K.gguf	Q5_K	2.16GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q5_K_M.gguf	Q5KM	2.16GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q5_1.gguf	Q5_1	2.28GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q6_K.gguf	Q6_K	2.46GB
Llama-3.2-3B-with-16bit-merged_lora_adapters-MOV_v2.Q8_0.gguf	Q8_0	3.19GB

Original model description: --- base_model: unsloth/Llama-3.2-3B language:

—en license: apache-2.0 tags:
—text-generation-inference
—transformers
—unsloth
—llama
—trl
—sft ---

Uploaded model

—Developed by: saqada
—License: apache-2.0
—Finetuned from model : unsloth/Llama-3.2-3B

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