You can deploy this model and start earning money today!

RichardErkhov/
lilmeaty_-_llama-gguf

Name: lilmeaty_-_llama-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama - GGUF

Model creator: https://huggingface.co/lilmeaty/
Original model: https://huggingface.co/lilmeaty/llama/

Name	Quant method	Size
llama.Q2_K.gguf	Q2_K	1.27GB
llama.IQ3_XS.gguf	IQ3_XS	1.38GB
llama.IQ3_S.gguf	IQ3_S	1.44GB
llama.Q3_K_S.gguf	Q3_K_S	1.44GB
llama.IQ3_M.gguf	IQ3_M	1.49GB
llama.Q3_K.gguf	Q3_K	1.57GB
llama.Q3_K_M.gguf	Q3_K_M	1.57GB
llama.Q3_K_L.gguf	Q3_K_L	1.69GB
llama.IQ4_XS.gguf	IQ4_XS	1.71GB
llama.Q4_0.gguf	Q4_0	1.79GB
llama.IQ4_NL.gguf	IQ4_NL	1.79GB
llama.Q4_K_S.gguf	Q4_K_S	1.8GB
llama.Q4_K.gguf	Q4_K	1.88GB
llama.Q4_K_M.gguf	Q4_K_M	1.88GB
llama.Q4_1.gguf	Q4_1	1.95GB
llama.Q5_0.gguf	Q5_0	2.11GB
llama.Q5_K_S.gguf	Q5_K_S	2.11GB
llama.Q5_K.gguf	Q5_K	2.16GB
llama.Q5_K_M.gguf	Q5_K_M	2.16GB
llama.Q5_1.gguf	Q5_1	2.28GB
llama.Q6_K.gguf	Q6_K	2.46GB
llama.Q8_0.gguf	Q8_0	3.19GB

Original model description:

base_model:

meta-llama/Llama-3.2-3B
PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B
meta-llama/Llama-3.2-3B-Instruct library_name: transformers tags:
mergekit
merge inference: true

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the breadcrumbs_ties merge method using meta-llama/Llama-3.2-3B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

merge_method: breadcrumbs_ties
base_model: meta-llama/Llama-3.2-3B
tokenizer_source: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B
dtype: bfloat16
parameters:
  normalize: true
models:
  - model: meta-llama/Llama-3.2-3B-Instruct
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        method: int8
        value: 100
      quantization:
        method: int4
        value: 100
  - model: PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B
    parameters:
      weight: 1
      density: 0.9
      gamma: 0.01
      normalize: true
      int8_mask: true
      random_seed: 0
      temperature: 0.5
      top_p: 0.65
      inference: true
      max_tokens: 999999999
      stream: true
      quantization:
        method: int8
        value: 100
      quantization:
        method: int4
        value: 100

RichardErkhov/lilmeaty_-_llama-gguf