README.md

---
language:
- en
base_model:
- meta-llama/Meta-Llama-3-8B-Instruct
library_name: transformers
tags:
- meta
- llama-3
- pytorch
- mergekit
- merge
license: llama3
license_link: LICENSE
pipeline_tag: text-generation
widget:
  - example_title: Hello
    messages:
    - role: user
      content: Hey my name is Corwin! How are you?
  - example_title: Hellriding out of Amber
    messages:
    - role: system
      content: You are a helpful and honest assistant. Please, respond concisely and truthfully.
    - role: user
      content: Can you recommend a good destination for a hellride out of Amber?
inference:
  parameters:
    max_new_tokens: 300
    stop:
    - <|end_of_text|>
    - <|eot_id|>
---
# llama-3-experiment-v1-9B-GGUF

This is an experimental merge, replicating additional layers to the model without post-merge healing. There is damage to the model, but it appears to be tolerable as is. The resulting impact on narrative text completion may be of interest.

Light testing performed with ChatML instruct prompting and sampler settings:
- temp=1 and minP=0.02
- temp=1 and smoothing factor=0.33

Full weights: [grimjim/llama-3-experiment-v1-9B](https://huggingface.co/grimjim/llama-3-experiment-v1-9B)

GGUF quants: [grimjim/llama-3-experiment-v1-9B-GGUF](https://huggingface.co/grimjim/llama-3-experiment-v1-9B-GGUF)

This is a merge of pre-trained language model meta-llama/Meta-Llama-3-8B-Instruct created using [mergekit](https://github.com/cg123/mergekit).

Built with Meta Llama 3.

## Merge Details
### Merge Method

This model was merged using the passthrough merge method.

### Models Merged

The following models were included in the merge:
* meta-llama/Meta-Llama-3-8B-Instruct

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
  - sources:
    - model: meta-llama/Meta-Llama-3-8B-Instruct
      layer_range: [0, 12]
  - sources:
    - model: meta-llama/Meta-Llama-3-8B-Instruct
      layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16

```