automerger commited on
Commit
f796d04
1 Parent(s): 6ade21e

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,28 +1,39 @@
1
  ---
2
- license: apache-2.0
3
- tags:
4
- - merge
5
- - mergekit
6
- - lazymergekit
7
  base_model:
 
8
  - mayacinka/yam-jom-7B-slerp
9
- - mayacinka/yam-jom-7B-ties
 
 
 
 
10
  ---
 
 
 
 
 
 
11
 
12
- # YamYam-7B
13
 
14
- YamYam-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
 
 
 
15
  * [mayacinka/yam-jom-7B-slerp](https://huggingface.co/mayacinka/yam-jom-7B-slerp)
16
- * [mayacinka/yam-jom-7B-ties](https://huggingface.co/mayacinka/yam-jom-7B-ties)
17
 
18
- ## 🧩 Configuration
 
 
19
 
20
  ```yaml
 
21
  slices:
22
  - sources:
23
  - model: mayacinka/yam-jom-7B-slerp
24
  layer_range: [0, 32]
25
- - model: mayacinka/yam-jom-7B-ties
26
  layer_range: [0, 32]
27
  merge_method: slerp
28
  base_model: mayacinka/yam-jom-7B-slerp
@@ -35,29 +46,5 @@ parameters:
35
  - value: 0.5
36
  dtype: bfloat16
37
  random_seed: 0
38
- ```
39
-
40
- ## 💻 Usage
41
-
42
- ```python
43
- !pip install -qU transformers accelerate
44
-
45
- from transformers import AutoTokenizer
46
- import transformers
47
- import torch
48
-
49
- model = "automerger/YamYam-7B"
50
- messages = [{"role": "user", "content": "What is a large language model?"}]
51
-
52
- tokenizer = AutoTokenizer.from_pretrained(model)
53
- prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
54
- pipeline = transformers.pipeline(
55
- "text-generation",
56
- model=model,
57
- torch_dtype=torch.float16,
58
- device_map="auto",
59
- )
60
-
61
- outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
62
- print(outputs[0]["generated_text"])
63
- ```
 
1
  ---
 
 
 
 
 
2
  base_model:
3
+ - mayacinka/yam-jom-7B
4
  - mayacinka/yam-jom-7B-slerp
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
  ---
11
+ # merge
12
+
13
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
+
15
+ ## Merge Details
16
+ ### Merge Method
17
 
18
+ This model was merged using the SLERP merge method.
19
 
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * [mayacinka/yam-jom-7B](https://huggingface.co/mayacinka/yam-jom-7B)
24
  * [mayacinka/yam-jom-7B-slerp](https://huggingface.co/mayacinka/yam-jom-7B-slerp)
 
25
 
26
+ ### Configuration
27
+
28
+ The following YAML configuration was used to produce this model:
29
 
30
  ```yaml
31
+
32
  slices:
33
  - sources:
34
  - model: mayacinka/yam-jom-7B-slerp
35
  layer_range: [0, 32]
36
+ - model: mayacinka/yam-jom-7B
37
  layer_range: [0, 32]
38
  merge_method: slerp
39
  base_model: mayacinka/yam-jom-7B-slerp
 
46
  - value: 0.5
47
  dtype: bfloat16
48
  random_seed: 0
49
+
50
+ ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
mergekit_config.yml CHANGED
@@ -3,7 +3,7 @@ slices:
3
  - sources:
4
  - model: mayacinka/yam-jom-7B-slerp
5
  layer_range: [0, 32]
6
- - model: mayacinka/yam-jom-7B-ties
7
  layer_range: [0, 32]
8
  merge_method: slerp
9
  base_model: mayacinka/yam-jom-7B-slerp
 
3
  - sources:
4
  - model: mayacinka/yam-jom-7B-slerp
5
  layer_range: [0, 32]
6
+ - model: mayacinka/yam-jom-7B
7
  layer_range: [0, 32]
8
  merge_method: slerp
9
  base_model: mayacinka/yam-jom-7B-slerp
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afdccf57e56d6ba1b3e1cf578cdc19b966618942f1da2636ed630059e9bbfa80
3
  size 9942981696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf14dae94c7657f0073eee02d4331d3f03fdc2caf5edc42baf3913fc04e7942
3
  size 9942981696
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:891fa7428d46fdf71b94ac59d71f3d725e10a575593e024b1557dc9824804283
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec711b3e4b8113989bcf30dd2b8b36dd6fda2d76d1e40ade9cee2def702cff8
3
  size 4540516344