altomek commited on
Commit
ff61f10
·
verified ·
1 Parent(s): 028339a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +44 -40
README.md CHANGED
@@ -1,40 +1,44 @@
1
- ---
2
- base_model: []
3
- library_name: transformers
4
- tags:
5
- - mergekit
6
- - merge
7
-
8
- ---
9
- # Coding-34B-U6-2
10
-
11
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
-
13
- ## Merge Details
14
- ### Merge Method
15
-
16
- This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using CodeLlama-34b-Instruct-hf-abliterated as a base.
17
-
18
- ### Models Merged
19
-
20
- The following models were included in the merge:
21
- * Samantha-1.11-CodeLlama-34b
22
- * WizardLM-1.0-Uncensored-CodeLlama-34b
23
- * CodeBooga-34B-v0.1
24
-
25
- ### Configuration
26
-
27
- The following YAML configuration was used to produce this model:
28
-
29
- ```yaml
30
- name: Coding-34B-U6-2
31
- models:
32
- - model: CodeLlama-34b-Instruct-hf-abliterated
33
- - model: Samantha-1.11-CodeLlama-34b
34
- - model: WizardLM-1.0-Uncensored-CodeLlama-34b
35
- - model: CodeBooga-34B-v0.1
36
- base_model: CodeLlama-34b-Instruct-hf-abliterated
37
- merge_method: model_stock
38
- dtype: float16
39
-
40
- ```
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - huihui-ai/CodeLlama-34b-Instruct-hf-abliterated
4
+ - QuixiAI/Samantha-1.11-CodeLlama-34b
5
+ - QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b
6
+ - oobabooga/CodeBooga-34B-v0.1
7
+ library_name: transformers
8
+ tags:
9
+ - mergekit
10
+ - merge
11
+
12
+ ---
13
+ <img src=https://cdn-uploads.huggingface.co/production/uploads/65a5ad3c0b5704678a8612b9/yORb0BvaM0ZMCYzec_j9N.png>
14
+ <a href="https://www.youtube.com/watch?v=9seZGfsfZM4" title="
15
+ Uplink Soundtrack: Karsten Koch - Blue Valley" target="_blank">intro music...</a>
16
+
17
+ ## Coding-34B-U6-2
18
+
19
+ Today models are trained on code so much. Have to check how some old ones fare with some assistant bits added ;P
20
+
21
+ ### Models Merged
22
+
23
+ The following models were included in the merge:
24
+ * Samantha-1.11-CodeLlama-34b
25
+ * WizardLM-1.0-Uncensored-CodeLlama-34b
26
+ * CodeBooga-34B-v0.1
27
+ * CodeLlama-34b-Instruct-hf-abliterated (as base)
28
+
29
+ ### Configuration
30
+
31
+ The following YAML configuration was used to produce this model:
32
+
33
+ ```yaml
34
+ name: Coding-34B-U6-2
35
+ models:
36
+ - model: CodeLlama-34b-Instruct-hf-abliterated
37
+ - model: Samantha-1.11-CodeLlama-34b
38
+ - model: WizardLM-1.0-Uncensored-CodeLlama-34b
39
+ - model: CodeBooga-34B-v0.1
40
+ base_model: CodeLlama-34b-Instruct-hf-abliterated
41
+ merge_method: model_stock
42
+ dtype: float16
43
+
44
+ ```