RichardErkhov/NobodyExistsOnTheInternet_-_code-llama-70b-python-instruct-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

code-llama-70b-python-instruct - GGUF

• Model creator: https://huggingface.co/NobodyExistsOnTheInternet/
• Original model: https://huggingface.co/NobodyExistsOnTheInternet/code-llama-70b-python-instruct/

Name	Quant method	Size
code-llama-70b-python-instruct.Q2_K.gguf	Q2_K	23.71GB
code-llama-70b-python-instruct.IQ3_XS.gguf	IQ3_XS	26.37GB
code-llama-70b-python-instruct.IQ3_S.gguf	IQ3_S	27.86GB
code-llama-70b-python-instruct.Q3_K_S.gguf	Q3_K_S	27.86GB
code-llama-70b-python-instruct.IQ3_M.gguf	IQ3_M	28.82GB
code-llama-70b-python-instruct.Q3_K.gguf	Q3_K	30.99GB
code-llama-70b-python-instruct.Q3_K_M.gguf	Q3_K_M	30.99GB
code-llama-70b-python-instruct.Q3_K_L.gguf	Q3_K_L	33.67GB
code-llama-70b-python-instruct.IQ4_XS.gguf	IQ4_XS	34.64GB
code-llama-70b-python-instruct.Q4_0.gguf	Q4_0	36.2GB
code-llama-70b-python-instruct.IQ4_NL.gguf	IQ4_NL	36.55GB
code-llama-70b-python-instruct.Q4_K_S.gguf	Q4_K_S	36.55GB
code-llama-70b-python-instruct.Q4_K.gguf	Q4_K	38.58GB
code-llama-70b-python-instruct.Q4_K_M.gguf	Q4_K_M	38.58GB
code-llama-70b-python-instruct.Q4_1.gguf	Q4_1	40.2GB
code-llama-70b-python-instruct.Q5_0.gguf	Q5_0	44.2GB
code-llama-70b-python-instruct.Q5_K_S.gguf	Q5_K_S	44.2GB
code-llama-70b-python-instruct.Q5_K.gguf	Q5_K	45.41GB
code-llama-70b-python-instruct.Q5_K_M.gguf	Q5_K_M	45.41GB
code-llama-70b-python-instruct.Q5_1.gguf	Q5_1	48.2GB
code-llama-70b-python-instruct.Q6_K.gguf	Q6_K	52.7GB
code-llama-70b-python-instruct.Q8_0.gguf	Q8_0	68.26GB

Original model description:

base_model: - meta-llama/Llama-2-70b-hf - codellama/CodeLlama-70b-Python-hf - codellama/CodeLlama-70b-Instruct-hf tags: - mergekit - merge license: mit

Codellama-python-instruct

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 meta-llama/Llama-2-70b-hf as a base.

Models Merged

The following models were included in the merge:

• codellama/CodeLlama-70b-Python-hf
• codellama/CodeLlama-70b-Instruct-hf

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: codellama/CodeLlama-70b-Python-hf
    parameters:
      density: 0.5
      weight: 0.5
  - model: codellama/CodeLlama-70b-Instruct-hf
    parameters:
      density: 0.5
      weight: 1.0
merge_method: dare_ties
base_model: meta-llama/Llama-2-70b-hf
parameters:
  # You can uncomment and set these parameters as needed
  # normalize: false
  # int8_mask: true
dtype: float16