timberrific commited on
Commit
0666b80
·
verified ·
1 Parent(s): cbbcf85

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  base_model:
3
- - johnsnowlabs/JSL-MedLlama-3-8B-v1.0
4
  - aaditya/OpenBioLLM-Llama3-8B
 
5
  library_name: transformers
6
  tags:
7
  - mergekit
@@ -15,7 +15,7 @@ This is a merge of pre-trained language models created using [mergekit](https://
15
  ## Merge Details
16
  ### Merge Method
17
 
18
- This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [aaditya/OpenBioLLM-Llama3-8B](https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B) as a base.
19
 
20
  ### Models Merged
21
 
@@ -29,12 +29,11 @@ The following YAML configuration was used to produce this model:
29
  ```yaml
30
  models:
31
  - model: aaditya/OpenBioLLM-Llama3-8B
32
- parameters:
33
- weight: 0.5
34
  - model: johnsnowlabs/JSL-MedLlama-3-8B-v1.0
35
  parameters:
 
36
  weight: 0.5
 
37
  base_model: aaditya/OpenBioLLM-Llama3-8B
38
- merge_method: task_arithmetic
39
  dtype: float16
40
  ```
 
1
  ---
2
  base_model:
 
3
  - aaditya/OpenBioLLM-Llama3-8B
4
+ - johnsnowlabs/JSL-MedLlama-3-8B-v1.0
5
  library_name: transformers
6
  tags:
7
  - mergekit
 
15
  ## Merge Details
16
  ### Merge Method
17
 
18
+ This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [aaditya/OpenBioLLM-Llama3-8B](https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B) as a base.
19
 
20
  ### Models Merged
21
 
 
29
  ```yaml
30
  models:
31
  - model: aaditya/OpenBioLLM-Llama3-8B
 
 
32
  - model: johnsnowlabs/JSL-MedLlama-3-8B-v1.0
33
  parameters:
34
+ density: 0.5
35
  weight: 0.5
36
+ merge_method: dare_ties
37
  base_model: aaditya/OpenBioLLM-Llama3-8B
 
38
  dtype: float16
39
  ```
mergekit_config.yml CHANGED
@@ -1,10 +1,9 @@
1
  models:
2
  - model: aaditya/OpenBioLLM-Llama3-8B
3
- parameters:
4
- weight: 0.5
5
  - model: johnsnowlabs/JSL-MedLlama-3-8B-v1.0
6
  parameters:
 
7
  weight: 0.5
 
8
  base_model: aaditya/OpenBioLLM-Llama3-8B
9
- merge_method: task_arithmetic
10
  dtype: float16
 
1
  models:
2
  - model: aaditya/OpenBioLLM-Llama3-8B
 
 
3
  - model: johnsnowlabs/JSL-MedLlama-3-8B-v1.0
4
  parameters:
5
+ density: 0.5
6
  weight: 0.5
7
+ merge_method: dare_ties
8
  base_model: aaditya/OpenBioLLM-Llama3-8B
 
9
  dtype: float16
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2556393edd37350038c475c6e574887114c0e97734756e27e3da6338c51d4a7f
3
  size 9976501216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:519fb7d2d2fc266f5e907388a0a249cda83414b4be0ee5a68e3236e79abca823
3
  size 9976501216
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43c568063263fff900b207cb0bce7f2056693cb9c5bb592345807134ce3ce2b9
3
  size 6084054888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faec43c2b16ad5f24a37815d1f987ac1354cb285ed3b777c217b749a8a79779e
3
  size 6084054888