Nelathan commited on
Commit
e2aa3d2
1 Parent(s): 31f23d8

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,10 +1,9 @@
1
  ---
2
  base_model:
3
- - Replete-AI/Replete-LLM-Qwen2-7b_Beta-Preview
4
- - MaziyarPanahi/calme-2.8-qwen2-7b
5
  - arcee-ai/Arcee-Spark
6
  - Weyaxi/Einstein-v7-Qwen2-7B
7
- - Qwen/Qwen2-7B
8
  library_name: transformers
9
  tags:
10
  - mergekit
@@ -19,7 +18,7 @@ This is a model created by merging several powerful language models:
19
 
20
  * **Base Model:** [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B)
21
  * **Merge Stock:**
22
- * [Replete-AI/Replete-LLM-Qwen2-7b_Beta-Preview](https://huggingface.co/Replete-AI/Replete-LLM-Qwen2-7b_Beta-Preview)
23
  * [MaziyarPanahi/calme-2.8-qwen2-7b](https://huggingface.co/MaziyarPanahi/calme-2.8-qwen2-7b)
24
  * [arcee-ai/Arcee-Spark](https://huggingface.co/arcee-ai/Arcee-Spark)
25
  * [Weyaxi/Einstein-v7-Qwen2-7B](https://huggingface.co/Weyaxi/Einstein-v7-Qwen2-7B)
@@ -32,7 +31,7 @@ FocusMix inherits the strengths of its component models, resulting in a model wi
32
 
33
  **Purpose:** aims to provide a powerful and versatile language model that excels in:
34
 
35
- * **Task-Specific Instructions:** FocusMix can effectively follow specific instructions and complete tasks with higher accuracy.
36
  * **Complex Reasoning:** The model can handle intricate prompts requiring logical deduction and problem-solving.
37
  * **Diverse Knowledge Domains:** FocusMix can engage in conversations and provide information across a wide range of topics.
38
 
@@ -44,7 +43,7 @@ The following YAML configuration was used to produce this model:
44
  merge_method: model_stock
45
  base_model: Qwen/Qwen2-7B
46
  models:
47
- - model: Replete-AI/Replete-LLM-Qwen2-7b_Beta-Preview
48
  - model: arcee-ai/Arcee-Spark
49
  - model: Weyaxi/Einstein-v7-Qwen2-7B
50
  - model: MaziyarPanahi/calme-2.8-qwen2-7b
 
1
  ---
2
  base_model:
3
+ - Replete-AI/Replete-LLM-Qwen2-7b
 
4
  - arcee-ai/Arcee-Spark
5
  - Weyaxi/Einstein-v7-Qwen2-7B
6
+ - MaziyarPanahi/calme-2.8-qwen2-7b
7
  library_name: transformers
8
  tags:
9
  - mergekit
 
18
 
19
  * **Base Model:** [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B)
20
  * **Merge Stock:**
21
+ * [Replete-AI/Replete-LLM-Qwen2-7b](https://huggingface.co/Replete-AI/Replete-LLM-Qwen2-7b)
22
  * [MaziyarPanahi/calme-2.8-qwen2-7b](https://huggingface.co/MaziyarPanahi/calme-2.8-qwen2-7b)
23
  * [arcee-ai/Arcee-Spark](https://huggingface.co/arcee-ai/Arcee-Spark)
24
  * [Weyaxi/Einstein-v7-Qwen2-7B](https://huggingface.co/Weyaxi/Einstein-v7-Qwen2-7B)
 
31
 
32
  **Purpose:** aims to provide a powerful and versatile language model that excels in:
33
 
34
+ * **Task-Specific Instructions:** FocusMix can effectively follow specific instructions and complete tasks with high accuracy.
35
  * **Complex Reasoning:** The model can handle intricate prompts requiring logical deduction and problem-solving.
36
  * **Diverse Knowledge Domains:** FocusMix can engage in conversations and provide information across a wide range of topics.
37
 
 
43
  merge_method: model_stock
44
  base_model: Qwen/Qwen2-7B
45
  models:
46
+ - model: Replete-AI/Replete-LLM-Qwen2-7b
47
  - model: arcee-ai/Arcee-Spark
48
  - model: Weyaxi/Einstein-v7-Qwen2-7B
49
  - model: MaziyarPanahi/calme-2.8-qwen2-7b
README2.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Replete-AI/Replete-LLM-Qwen2-7b
4
+ - Qwen/Qwen2-7B
5
+ - MaziyarPanahi/calme-2.8-qwen2-7b
6
+ - arcee-ai/Arcee-Spark
7
+ - Weyaxi/Einstein-v7-Qwen2-7B
8
+ library_name: transformers
9
+ tags:
10
+ - mergekit
11
+ - merge
12
+
13
+ ---
14
+ # Qwen2-7B-FocusMix
15
+
16
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
17
+
18
+ ## Merge Details
19
+ ### Merge Method
20
+
21
+ This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) as a base.
22
+
23
+ ### Models Merged
24
+
25
+ The following models were included in the merge:
26
+ * [Replete-AI/Replete-LLM-Qwen2-7b](https://huggingface.co/Replete-AI/Replete-LLM-Qwen2-7b)
27
+ * [MaziyarPanahi/calme-2.8-qwen2-7b](https://huggingface.co/MaziyarPanahi/calme-2.8-qwen2-7b)
28
+ * [arcee-ai/Arcee-Spark](https://huggingface.co/arcee-ai/Arcee-Spark)
29
+ * [Weyaxi/Einstein-v7-Qwen2-7B](https://huggingface.co/Weyaxi/Einstein-v7-Qwen2-7B)
30
+
31
+ ### Configuration
32
+
33
+ The following YAML configuration was used to produce this model:
34
+
35
+ ```yaml
36
+ merge_method: model_stock
37
+ base_model: Qwen/Qwen2-7B
38
+ models:
39
+ - model: Replete-AI/Replete-LLM-Qwen2-7b
40
+ - model: arcee-ai/Arcee-Spark
41
+ - model: Weyaxi/Einstein-v7-Qwen2-7B
42
+ - model: MaziyarPanahi/calme-2.8-qwen2-7b
43
+ dtype: bfloat16
44
+ tokenizer_source: base
45
+ ```
mergekit_config.yml CHANGED
@@ -1,7 +1,7 @@
1
  merge_method: model_stock
2
  base_model: Qwen/Qwen2-7B
3
  models:
4
- - model: Replete-AI/Replete-LLM-Qwen2-7b_Beta-Preview
5
  - model: arcee-ai/Arcee-Spark
6
  - model: Weyaxi/Einstein-v7-Qwen2-7B
7
  - model: MaziyarPanahi/calme-2.8-qwen2-7b
 
1
  merge_method: model_stock
2
  base_model: Qwen/Qwen2-7B
3
  models:
4
+ - model: Replete-AI/Replete-LLM-Qwen2-7b
5
  - model: arcee-ai/Arcee-Spark
6
  - model: Weyaxi/Einstein-v7-Qwen2-7B
7
  - model: MaziyarPanahi/calme-2.8-qwen2-7b
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ffa4ab38a97d1c26dc7c600f199323f519d470cff31302244a4585681421920
3
+ size 4970706328
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64737fd28fb1b92f7219d8b4761191445d99eb88d5be0f0df235aa41a5da6fe
3
+ size 4932751032
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c76156caa4600aaeb8b1446fcfe58d5c35efe55ff47cc00051aa46c85c05cc5d
3
+ size 4991495808
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:321857587f63d61d75337fed4595ef9206d8d0350592690c73b8a9cd54ffdc2b
3
+ size 330326240