CoolFace
Modelpublic

RichardErkhov/ProjectZLLM_-_SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes2.4kdownloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged - GGUF

  • —Model creator: https://huggingface.co/ProjectZLLM/
  • —Original model: https://huggingface.co/ProjectZLLM/SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged/
NameQuant methodSize
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q2_K.ggufQ2_K2.96GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.IQ3_XS.ggufIQ3_XS3.28GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.IQ3_S.ggufIQ3_S3.43GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q3_K_S.ggufQ3KS3.41GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.IQ3_M.ggufIQ3_M3.52GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q3_K.ggufQ3_K3.74GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q3_K_M.ggufQ3KM3.74GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q3_K_L.ggufQ3KL4.03GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.IQ4_XS.ggufIQ4_XS4.18GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q4_0.ggufQ4_04.34GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.IQ4_NL.ggufIQ4_NL4.38GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q4_K_S.ggufQ4KS4.37GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q4_K.ggufQ4_K4.58GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q4_K_M.ggufQ4KM4.58GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q4_1.ggufQ4_14.78GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q5_0.ggufQ5_05.21GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q5_K_S.ggufQ5KS5.21GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q5_K.ggufQ5_K5.34GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q5_K_M.ggufQ5KM5.34GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q5_1.ggufQ5_15.65GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q6_K.ggufQ6_K6.14GB
SFT-dna-Llama-3.1-8B-Instruct-20-r16_merged.Q8_0.ggufQ8_07.95GB

Original model description: --- base_model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit language:

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

Uploaded model

  • —Developed by: TifTifR
  • —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.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>