shidowake_-_test-240115-mergekit-CodeLlama-Swallow-7b-instruct-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

test-240115-mergekit-CodeLlama-Swallow-7b-instruct - bnb 8bits

• Model creator: https://huggingface.co/shidowake/
• Original model: https://huggingface.co/shidowake/test-240115-mergekit-CodeLlama-Swallow-7b-instruct/

Original model description:

base_model:

• codellama/CodeLlama-7b-Python-hf
• tokyotech-llm/Swallow-7b-instruct-hf tags:
• mergekit
• merge

---

merged-output

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 tokyotech-llm/Swallow-7b-instruct-hf as a base.

Models Merged

The following models were included in the merge:

• codellama/CodeLlama-7b-Python-hf

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: tokyotech-llm/Swallow-7b-instruct-hf
    # no parameters necessary for base model
  - model: codellama/CodeLlama-7b-Python-hf # follow user intent 
    parameters:
      density: 1
      weight:
      - filter: mlp.down_proj
        value: [0.3, 0.25, 0.25, 0.15, 0.1]
      - filter: mlp.gate_proj
        value: [0.7, 0.25, 0.5, 0.45, 0.4]
      - filter: mlp.up_proj
        value: [0.7, 0.25, 0.5, 0.45, 0.4]
      - filter: self_attn
        value: [0.7, 0.25, 0.5, 0.45, 0.4]
      - value: 0 # fallback for rest of tensors.
merge_method: dare_ties
base_model: tokyotech-llm/Swallow-7b-instruct-hf
dtype: bfloat16
tokenizer_source: union