Modelpublic

RichardErkhov/saqada_-_Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes455downloads

Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.1-8B-with-16bit-mergedloraadapters-MOV_v7 - GGUF

—Model creator: https://huggingface.co/saqada/
—Original model: https://huggingface.co/saqada/Llama-3.1-8B-with-16bit-mergedloraadapters-MOV_v7/

Name	Quant method	Size
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q2_K.gguf	Q2_K	2.96GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.IQ3_XS.gguf	IQ3_XS	3.28GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.IQ3_S.gguf	IQ3_S	3.43GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q3_K_S.gguf	Q3KS	3.41GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.IQ3_M.gguf	IQ3_M	3.52GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q3_K.gguf	Q3_K	3.74GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q3_K_M.gguf	Q3KM	3.74GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q3_K_L.gguf	Q3KL	4.03GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q4_0.gguf	Q4_0	4.34GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q4_K_S.gguf	Q4KS	4.37GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q4_K.gguf	Q4_K	4.58GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q4_K_M.gguf	Q4KM	4.58GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q4_1.gguf	Q4_1	4.78GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q5_0.gguf	Q5_0	5.21GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q5_K_S.gguf	Q5KS	5.21GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q5_K.gguf	Q5_K	5.34GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q5_K_M.gguf	Q5KM	5.34GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q5_1.gguf	Q5_1	5.65GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q6_K.gguf	Q6_K	6.14GB
Llama-3.1-8B-with-16bit-merged_lora_adapters-MOV_v7.Q8_0.gguf	Q8_0	7.95GB

Original model description: --- base_model: unsloth/Meta-Llama-3.1-8B-Instruct tags:

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

Uploaded model

—Developed by: saqada
—License: apache-2.0
—Finetuned from model : unsloth/Meta-Llama-3.1-8B-Instruct

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