Update README.md
Browse files
README.md
CHANGED
@@ -11,6 +11,10 @@ base_model:
|
|
11 |
|
12 |
# meta-LLama3-6B-PruneMe-TEST-21_29
|
13 |
|
|
|
|
|
|
|
|
|
14 |
meta-LLama3-6B-PruneMe-TEST-21_29 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
15 |
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
16 |
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
|
|
11 |
|
12 |
# meta-LLama3-6B-PruneMe-TEST-21_29
|
13 |
|
14 |
+
This model was pruned after being analyzed with [PruneMe](https://github.com/arcee-ai/PruneMe)
|
15 |
+
|
16 |
+
*INFO: This model is not usable as is, and it must be 'healed' from pruning using techinques detailed in [The Unreasonable Ineffectiveness of the Deeper Layers](https://arxiv.org/abs/2403.17887).*
|
17 |
+
|
18 |
meta-LLama3-6B-PruneMe-TEST-21_29 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
19 |
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
20 |
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|