README.md

metadata

language:
  - en
base_model:
  - grimjim/Llama-3-Luminurse-v0.1-OAS-8B
library_name: transformers
quanted_by: grimjim
license: cc-by-nc-4.0
pipeline_tag: text-generation

Llama-3-Luminurse-v0.1-OAS-8B-GGUF

WARNING: Older versions of llama-cpp may not properly support the tokenizer. Please update.

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

Given that a biomedical model was merged with Lumimaid, the obvious resulting name was Luminurse.

• Full weights
• GGUF quants c/o mradermacher
• iMatrix GGUF quants c/o mradermacher

Built with Meta Llama 3.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
• grimjim/llama-3-aaditya-OpenBioLLM-8B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
      layer_range: [0,32]
    - model: grimjim/llama-3-aaditya-OpenBioLLM-8B
      layer_range: [0,32]
merge_method: slerp
base_model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
parameters:
  t:
    - value: 0.1
dtype: bfloat16