RichardErkhov/Badgids_-_Gonzo-Code-7B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Gonzo-Code-7B - GGUF

• Model creator: https://huggingface.co/Badgids/
• Original model: https://huggingface.co/Badgids/Gonzo-Code-7B/

Name	Quant method	Size
Gonzo-Code-7B.Q2_K.gguf	Q2_K	2.53GB
Gonzo-Code-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
Gonzo-Code-7B.IQ3_S.gguf	IQ3_S	2.96GB
Gonzo-Code-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
Gonzo-Code-7B.IQ3_M.gguf	IQ3_M	3.06GB
Gonzo-Code-7B.Q3_K.gguf	Q3_K	3.28GB
Gonzo-Code-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
Gonzo-Code-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
Gonzo-Code-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
Gonzo-Code-7B.Q4_0.gguf	Q4_0	3.83GB
Gonzo-Code-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
Gonzo-Code-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
Gonzo-Code-7B.Q4_K.gguf	Q4_K	4.07GB
Gonzo-Code-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
Gonzo-Code-7B.Q4_1.gguf	Q4_1	4.24GB
Gonzo-Code-7B.Q5_0.gguf	Q5_0	4.65GB
Gonzo-Code-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
Gonzo-Code-7B.Q5_K.gguf	Q5_K	4.78GB
Gonzo-Code-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
Gonzo-Code-7B.Q5_1.gguf	Q5_1	5.07GB
Gonzo-Code-7B.Q6_K.gguf	Q6_K	5.53GB
Gonzo-Code-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

base_model: - eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO - Nondzu/Mistral-7B-Instruct-v0.2-code-ft - xingyaoww/CodeActAgent-Mistral-7b-v0.1 - beowolx/MistralHermes-CodePro-7B-v1 library_name: transformers tags: - mergekit - merge license: apache-2.0 language: - en

Gonzo-Code-7B

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO as a base.

Models Merged

The following models were included in the merge:

• Nondzu/Mistral-7B-Instruct-v0.2-code-ft
• xingyaoww/CodeActAgent-Mistral-7b-v0.1
• beowolx/MistralHermes-CodePro-7B-v1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO
    # No parameters necessary for base model
  - model: xingyaoww/CodeActAgent-Mistral-7b-v0.1
    parameters:
      density: 0.53
      weight: 0.4
  - model: Nondzu/Mistral-7B-Instruct-v0.2-code-ft 
    parameters:
      density: 0.53
      weight: 0.3
  - model: beowolx/MistralHermes-CodePro-7B-v1
    parameters:
      density: 0.53
      weight: 0.3
merge_method: dare_ties
base_model: eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO
parameters:
  int8_mask: true
dtype: bfloat16