You can deploy this model and start earning money today!

RichardErkhov/
ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf

Name: ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties - GGUF

Model creator: https://huggingface.co/ank028/
Original model: https://huggingface.co/ank028/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties/

Name	Quant method	Size
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q2_K.gguf	Q2_K	0.54GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ3_XS.gguf	IQ3_XS	0.58GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ3_S.gguf	IQ3_S	0.6GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q3_K_S.gguf	Q3_K_S	0.6GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ3_M.gguf	IQ3_M	0.61GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q3_K.gguf	Q3_K	0.64GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q3_K_M.gguf	Q3_K_M	0.64GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q3_K_L.gguf	Q3_K_L	0.68GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ4_XS.gguf	IQ4_XS	0.7GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_0.gguf	Q4_0	0.72GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ4_NL.gguf	IQ4_NL	0.72GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_K_S.gguf	Q4_K_S	0.72GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_K.gguf	Q4_K	0.75GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_K_M.gguf	Q4_K_M	0.75GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_1.gguf	Q4_1	0.77GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_0.gguf	Q5_0	0.83GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_K_S.gguf	Q5_K_S	0.83GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_K.gguf	Q5_K	0.85GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_K_M.gguf	Q5_K_M	0.85GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_1.gguf	Q5_1	0.89GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q6_K.gguf	Q6_K	0.95GB
Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q8_0.gguf	Q8_0	1.23GB

Original model description:

base_model:

ank028/Llama-3.2-1B-Instruct-medmcqa
meta-llama/Llama-3.2-1B-Instruct
autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1 library_name: transformers tags:
mergekit
merge

m_l

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 meta-llama/Llama-3.2-1B-Instruct 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: ank028/Llama-3.2-1B-Instruct-medmcqa
    parameters:
      density: 0.5 # density gradient
      weight: 1.0
  - model: autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1
    parameters:
      density: 0.5
      weight: 0.5 # weight gradient
merge_method: ties
base_model: meta-llama/Llama-3.2-1B-Instruct
parameters:
  normalize: true
  int8_mask: false
dtype: float16
name: Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties

RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf