You can deploy this model and start earning money today!

RichardErkhov/
Theros_-_llama3.2-CharReflectBase-3B-gguf

Name: Theros_-_llama3.2-CharReflectBase-3B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama3.2-CharReflectBase-3B - GGUF

Model creator: https://huggingface.co/Theros/
Original model: https://huggingface.co/Theros/llama3.2-CharReflectBase-3B/

Name	Quant method	Size
llama3.2-CharReflectBase-3B.Q2_K.gguf	Q2_K	1.27GB
llama3.2-CharReflectBase-3B.IQ3_XS.gguf	IQ3_XS	1.38GB
llama3.2-CharReflectBase-3B.IQ3_S.gguf	IQ3_S	1.44GB
llama3.2-CharReflectBase-3B.Q3_K_S.gguf	Q3_K_S	1.44GB
llama3.2-CharReflectBase-3B.IQ3_M.gguf	IQ3_M	1.49GB
llama3.2-CharReflectBase-3B.Q3_K.gguf	Q3_K	1.57GB
llama3.2-CharReflectBase-3B.Q3_K_M.gguf	Q3_K_M	1.57GB
llama3.2-CharReflectBase-3B.Q3_K_L.gguf	Q3_K_L	1.69GB
llama3.2-CharReflectBase-3B.IQ4_XS.gguf	IQ4_XS	1.71GB
llama3.2-CharReflectBase-3B.Q4_0.gguf	Q4_0	1.79GB
llama3.2-CharReflectBase-3B.IQ4_NL.gguf	IQ4_NL	1.79GB
llama3.2-CharReflectBase-3B.Q4_K_S.gguf	Q4_K_S	1.8GB
llama3.2-CharReflectBase-3B.Q4_K.gguf	Q4_K	1.88GB
llama3.2-CharReflectBase-3B.Q4_K_M.gguf	Q4_K_M	1.88GB
llama3.2-CharReflectBase-3B.Q4_1.gguf	Q4_1	1.95GB
llama3.2-CharReflectBase-3B.Q5_0.gguf	Q5_0	2.11GB
llama3.2-CharReflectBase-3B.Q5_K_S.gguf	Q5_K_S	2.11GB
llama3.2-CharReflectBase-3B.Q5_K.gguf	Q5_K	2.16GB
llama3.2-CharReflectBase-3B.Q5_K_M.gguf	Q5_K_M	2.16GB
llama3.2-CharReflectBase-3B.Q5_1.gguf	Q5_1	2.28GB
llama3.2-CharReflectBase-3B.Q6_K.gguf	Q6_K	2.46GB
llama3.2-CharReflectBase-3B.Q8_0.gguf	Q8_0	3.19GB

Original model description:

base_model:

Orion-zhen/Reflection-Llama3.2-3B-Instruct
chuanli11/Llama-3.2-3B-Instruct-uncensored
bunnycore/Llama-3.2-3B-RP-LORA
ericflo/Llama-3.2-3B-COT
ericflo/Llama-3.2-3B-COT
bunnycore/Llama-3.2-3B-General-lora_model library_name: transformers tags:
mergekit
merge

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using ericflo/Llama-3.2-3B-COT 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

models:
  - model: Orion-zhen/Reflection-Llama3.2-3B-Instruct
    parameters:
      density: 0.5
      weight: 0.5
  - model: ericflo/Llama-3.2-3B-COT+bunnycore/Llama-3.2-3B-General-lora_model
    parameters:
      density: 0.2
      weight: 0.2
  - model: chuanli11/Llama-3.2-3B-Instruct-uncensored+bunnycore/Llama-3.2-3B-RP-LORA
    parameters:
      density: 0.3
      weight: 0.3
merge_method: ties
base_model: ericflo/Llama-3.2-3B-COT
parameters:
  density: 1
  normalize: false
  int8_mask: true
dtype: float16

RichardErkhov/Theros_-_llama3.2-CharReflectBase-3B-gguf