RichardErkhov/Hjgugugjhuhjggg_-_mergekit-ties-xzdpqzs-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mergekit-ties-xzdpqzs - GGUF

• Model creator: https://huggingface.co/Hjgugugjhuhjggg/
• Original model: https://huggingface.co/Hjgugugjhuhjggg/mergekit-ties-xzdpqzs/

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

Original model description:

base_model:

• huyhoangt2201/llama-3.2-1b-sql_finetuned_billingual_3.0_merged
• jayavibhav/llama3.2_1b_CoT
• huyhoangt2201/llama-3.2-1b-chat-sql3-merged
• autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1
• Alelcv27/llama3.2-1b-math-code
• unsloth/Llama-3.2-1B-Instruct-bnb-4bit
• meta-llama/Llama-3.2-1B
• student-abdullah/Llama3.2-1B_Hinglish-Medicine-Dataset_Finetuning_28-09
• meta-llama/Llama-3.2-1B-Instruct
• MLking2/llama-3.2-1b-medical
• autoprogrammer/Llama-3.2-1B-Instruct-medmcqa-zh-linear 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 meta-llama/Llama-3.2-1B-Instruct as a base.

Models Merged

The following models were included in the merge:

• huyhoangt2201/llama-3.2-1b-sql_finetuned_billingual_3.0_merged
• jayavibhav/llama3.2_1b_CoT
• huyhoangt2201/llama-3.2-1b-chat-sql3-merged
• autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1
• Alelcv27/llama3.2-1b-math-code
• unsloth/Llama-3.2-1B-Instruct-bnb-4bit
• meta-llama/Llama-3.2-1B
• student-abdullah/Llama3.2-1B_Hinglish-Medicine-Dataset_Finetuning_28-09
• MLking2/llama-3.2-1b-medical
• autoprogrammer/Llama-3.2-1B-Instruct-medmcqa-zh-linear

Configuration

The following YAML configuration was used to produce this model:

merge_method: ties
architectures: ["transformer"]
base_model: meta-llama/Llama-3.2-1B-Instruct

models:
  - model: Alelcv27/llama3.2-1b-math-code
  - model: huyhoangt2201/llama-3.2-1b-sql_finetuned_billingual_3.0_merged
  - model: autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1
  - model: meta-llama/Llama-3.2-1B-Instruct
  - model: autoprogrammer/Llama-3.2-1B-Instruct-medmcqa-zh-linear
  - model: meta-llama/Llama-3.2-1B
  - model: unsloth/Llama-3.2-1B-Instruct-bnb-4bit
  - model: MLking2/llama-3.2-1b-medical
  - model: jayavibhav/llama3.2_1b_CoT
  - model: huyhoangt2201/llama-3.2-1b-chat-sql3-merged
  - model: student-abdullah/Llama3.2-1B_Hinglish-Medicine-Dataset_Finetuning_28-09

parameters:
  density: 0.5
  weight: 1.0
  int8_mask: true
  normalize: true