Update README.md
Browse files
README.md
CHANGED
@@ -11,14 +11,14 @@ base_model:
|
|
11 |
- meta-llama/Meta-Llama-3-8B-Instruct
|
12 |
---
|
13 |
|
14 |
-
#
|
15 |
|
16 |
This model was pruned after being analyzed with [PruneMe](https://github.com/arcee-ai/PruneMe)
|
17 |
|
18 |
*INFO:root:Layer 22 to 30 has the minimum average distance of 0.26598974609375. Consider examining this layer more closely for potential optimization or removal.*
|
19 |
|
20 |
|
21 |
-
|
22 |
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
23 |
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
24 |
|
@@ -45,7 +45,7 @@ from transformers import AutoTokenizer
|
|
45 |
import transformers
|
46 |
import torch
|
47 |
|
48 |
-
model = "jsfs11/
|
49 |
messages = [{"role": "user", "content": "What is a large language model?"}]
|
50 |
|
51 |
tokenizer = AutoTokenizer.from_pretrained(model)
|
|
|
11 |
- meta-llama/Meta-Llama-3-8B-Instruct
|
12 |
---
|
13 |
|
14 |
+
# meta-LLama3-8b-PruneME-TEST-22_30
|
15 |
|
16 |
This model was pruned after being analyzed with [PruneMe](https://github.com/arcee-ai/PruneMe)
|
17 |
|
18 |
*INFO:root:Layer 22 to 30 has the minimum average distance of 0.26598974609375. Consider examining this layer more closely for potential optimization or removal.*
|
19 |
|
20 |
|
21 |
+
meta-LLama3-8b-PruneME-TEST-22_30 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
22 |
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
23 |
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
24 |
|
|
|
45 |
import transformers
|
46 |
import torch
|
47 |
|
48 |
+
model = "jsfs11/meta-LLama3-8b-PruneME-TEST-22_30"
|
49 |
messages = [{"role": "user", "content": "What is a large language model?"}]
|
50 |
|
51 |
tokenizer = AutoTokenizer.from_pretrained(model)
|