129 lines
3.1 KiB
Markdown
129 lines
3.1 KiB
Markdown
---
|
|
base_model:
|
|
- meta-llama/Llama-2-7b-hf
|
|
- meta-llama/CodeLlama-7b-hf
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
license: llama2
|
|
model-index:
|
|
- name: coma-7B-v0.1
|
|
results:
|
|
- task:
|
|
type: text-generation
|
|
dataset:
|
|
type: lm-evaluation-harness
|
|
name: bbh
|
|
metrics:
|
|
- name: acc_norm
|
|
type: acc_norm
|
|
value: 0.3355
|
|
verified: false
|
|
- task:
|
|
type: text-generation
|
|
dataset:
|
|
type: lm-evaluation-harness
|
|
name: gpqa
|
|
metrics:
|
|
- name: acc_norm
|
|
type: acc_norm
|
|
value: 0.2587
|
|
verified: false
|
|
- task:
|
|
type: text-generation
|
|
dataset:
|
|
type: lm-evaluation-harness
|
|
name: math
|
|
metrics:
|
|
- name: exact_match
|
|
type: exact_match
|
|
value: 0.0104
|
|
verified: false
|
|
- task:
|
|
type: text-generation
|
|
dataset:
|
|
type: lm-evaluation-harness
|
|
name: mmlu
|
|
metrics:
|
|
- name: acc_norm
|
|
type: acc_norm
|
|
value: 0.1433
|
|
verified: false
|
|
- task:
|
|
type: text-generation
|
|
dataset:
|
|
type: lm-evaluation-harness
|
|
name: musr
|
|
metrics:
|
|
- name: acc_norm
|
|
type: acc_norm
|
|
value: 0.3844
|
|
verified: false
|
|
- task:
|
|
type: text-generation
|
|
dataset:
|
|
type: lm-evaluation-harness
|
|
name: hellaswag
|
|
metrics:
|
|
- name: acc
|
|
type: acc
|
|
value: 0.5182234614618602
|
|
verified: false
|
|
- name: acc_norm
|
|
type: acc_norm
|
|
value: 0.6834295956980682
|
|
verified: false
|
|
---
|
|
[<img src="https://raw.githubusercontent.com/csabakecskemeti/devquasar/main/dq_logo_black-transparent.png" width="200"/>](https://devquasar.com)
|
|
|
|
'Make knowledge free for everyone'
|
|
|
|
<a href='https://ko-fi.com/L4L416YX7C' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>
|
|
|
|
|
|
|
|
# coma-7B-v0.1
|
|
|
|
|
|
|
|
CodeLlama + Llama = CoMa :)
|
|
This is an experiment to try merged models
|
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
Quantized version: [DevQuasar/coma-7B-v0.1-GGUF](https://huggingface.co/DevQuasar/coma-7B-v0.1-GGUF)
|
|
## Merge Details
|
|
### Merge Method
|
|
|
|
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
|
|
|
|
### Models Merged
|
|
"Blast from the Past" :D
|
|
The following models were included in the merge:
|
|
* [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf)
|
|
* [meta-llama/CodeLlama-7b-hf](https://huggingface.co/meta-llama/CodeLlama-7b-hf)
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
models:
|
|
- model: meta-llama/Llama-2-7b-hf
|
|
parameters:
|
|
weight: 1.0
|
|
- model: meta-llama/CodeLlama-7b-hf
|
|
parameters:
|
|
weight: 0.5
|
|
merge_method: linear
|
|
dtype: float16
|
|
|
|
```
|
|
|
|
|
|
I'm doing this to 'Make knowledge free for everyone', using my personal time and resources.
|
|
|
|
If you want to support my efforts please visit my ko-fi page: https://ko-fi.com/devquasar
|
|
|
|
Also feel free to visit my website https://devquasar.com/ |