CoolFace
Modelpublic

RichardErkhov/belyakoff_-_llama-3.2-3b-instruct-fine-tuned-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes475downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3.2-3b-instruct-fine-tuned - GGUF

  • —Model creator: https://huggingface.co/belyakoff/
  • —Original model: https://huggingface.co/belyakoff/llama-3.2-3b-instruct-fine-tuned/
NameQuant methodSize
llama-3.2-3b-instruct-fine-tuned.Q2_K.ggufQ2_K1.27GB
llama-3.2-3b-instruct-fine-tuned.IQ3_XS.ggufIQ3_XS1.38GB
llama-3.2-3b-instruct-fine-tuned.IQ3_S.ggufIQ3_S1.44GB
llama-3.2-3b-instruct-fine-tuned.Q3_K_S.ggufQ3KS1.44GB
llama-3.2-3b-instruct-fine-tuned.IQ3_M.ggufIQ3_M1.49GB
llama-3.2-3b-instruct-fine-tuned.Q3_K.ggufQ3_K1.57GB
llama-3.2-3b-instruct-fine-tuned.Q3_K_M.ggufQ3KM1.57GB
llama-3.2-3b-instruct-fine-tuned.Q3_K_L.ggufQ3KL1.69GB
llama-3.2-3b-instruct-fine-tuned.IQ4_XS.ggufIQ4_XS1.71GB
llama-3.2-3b-instruct-fine-tuned.Q4_0.ggufQ4_01.79GB
llama-3.2-3b-instruct-fine-tuned.IQ4_NL.ggufIQ4_NL1.79GB
llama-3.2-3b-instruct-fine-tuned.Q4_K_S.ggufQ4KS1.8GB
llama-3.2-3b-instruct-fine-tuned.Q4_K.ggufQ4_K1.88GB
llama-3.2-3b-instruct-fine-tuned.Q4_K_M.ggufQ4KM1.88GB
llama-3.2-3b-instruct-fine-tuned.Q4_1.ggufQ4_11.95GB
llama-3.2-3b-instruct-fine-tuned.Q5_0.ggufQ5_02.11GB
llama-3.2-3b-instruct-fine-tuned.Q5_K_S.ggufQ5KS2.11GB
llama-3.2-3b-instruct-fine-tuned.Q5_K.ggufQ5_K2.16GB
llama-3.2-3b-instruct-fine-tuned.Q5_K_M.ggufQ5KM2.16GB
llama-3.2-3b-instruct-fine-tuned.Q5_1.ggufQ5_12.28GB
llama-3.2-3b-instruct-fine-tuned.Q6_K.ggufQ6_K2.46GB
llama-3.2-3b-instruct-fine-tuned.Q8_0.ggufQ8_03.19GB

Original model description: --- library_name: transformers datasets:

  • —Vikhrmodels/GrandMaster-PRO-MAX
  • —Vikhrmodels/Grounded-RAG-RU-v2 language:
  • —ru
  • —en base_model:
  • —meta-llama/Llama-3.2-3B-Instruct pipeline_tag: text-generation license: apache-2.0 tags:
  • —code
  • —rag
  • —question answering ---