LoneStriker
commited on
Commit
•
28b961a
1
Parent(s):
eb16306
Upload folder using huggingface_hub
Browse files- .gitattributes +9 -35
- Everyone-Coder-33b-v2-Base-Q3_K_L.gguf +3 -0
- Everyone-Coder-33b-v2-Base-Q3_K_M.gguf +3 -0
- Everyone-Coder-33b-v2-Base-Q3_K_S.gguf +3 -0
- Everyone-Coder-33b-v2-Base-Q4_K_M.gguf +3 -0
- Everyone-Coder-33b-v2-Base-Q4_K_S.gguf +3 -0
- Everyone-Coder-33b-v2-Base-Q5_K_M.gguf +3 -0
- Everyone-Coder-33b-v2-Base-Q5_K_S.gguf +3 -0
- Everyone-Coder-33b-v2-Base-Q6_K.gguf +3 -0
- Everyone-Coder-33b-v2-Base-Q8_0.gguf +3 -0
- README.md +59 -0
.gitattributes
CHANGED
@@ -1,35 +1,9 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
-
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
-
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
-
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
-
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
-
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
-
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
1 |
+
Everyone-Coder-33b-v2-Base-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
2 |
+
Everyone-Coder-33b-v2-Base-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
3 |
+
Everyone-Coder-33b-v2-Base-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
4 |
+
Everyone-Coder-33b-v2-Base-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
5 |
+
Everyone-Coder-33b-v2-Base-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
6 |
+
Everyone-Coder-33b-v2-Base-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
7 |
+
Everyone-Coder-33b-v2-Base-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
8 |
+
Everyone-Coder-33b-v2-Base-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
9 |
+
Everyone-Coder-33b-v2-Base-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Everyone-Coder-33b-v2-Base-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:598530c73a6d3a0ca592f978c4a43c2de93a47a150620805dcc2174d4a977bdf
|
3 |
+
size 17560367200
|
Everyone-Coder-33b-v2-Base-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3aaf2d3812062defade64be95ad551dd4ba5451684a116872887bcaa3918c62
|
3 |
+
size 16092131424
|
Everyone-Coder-33b-v2-Base-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3c11312e832a6a48f5d1f687d6b30d9da4f00c9e7838fa93e7677b02a4a5606
|
3 |
+
size 14421901408
|
Everyone-Coder-33b-v2-Base-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78ebe82af6f1bf5b5cda54e0580687ac429c1f491156e49523b3e66cc12727b0
|
3 |
+
size 19940659296
|
Everyone-Coder-33b-v2-Base-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9351a20fbc2698b7eecc2edb9f95815b5d62b76b88e61d265d34b3003856157
|
3 |
+
size 18943533152
|
Everyone-Coder-33b-v2-Base-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8edea21c392853a80d23690372dd432049ffcde35d9af4a3e513cea319721182
|
3 |
+
size 23535898720
|
Everyone-Coder-33b-v2-Base-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:626f6e67495509faaddbb93fc736bc893269ef468a1cf9e2ba656b907e98a702
|
3 |
+
size 22958301280
|
Everyone-Coder-33b-v2-Base-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9793efbf0797464ca83651a52ba0facbc69f61d1c93ae26b50e2e64f53796506
|
3 |
+
size 27355840608
|
Everyone-Coder-33b-v2-Base-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fad07fb26afc70b4df008116ae79de216be32c70b7fc0deaf4579abf4cb384af
|
3 |
+
size 35430879328
|
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
|
3 |
+
license: other
|
4 |
+
license_name: deepseek
|
5 |
+
license_link: https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/LICENSE-MODEL
|
6 |
+
tags:
|
7 |
+
- merge
|
8 |
+
---
|
9 |
+
Everyone-Coder-33b-v2-Base
|
10 |
+
|
11 |
+
|
12 |
+
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/ECrHQnZnv8UM9GUCQtlWW.jpeg)
|
13 |
+
|
14 |
+
EveryoneLLM series of models made by the community, for the community. This is a coding specific model made using fine-tunes of deekseekcoder-33b-base.
|
15 |
+
|
16 |
+
This Version 2 of the Everything-Coder-33b model uses the task_arithmetic merging method which has major increases in coding performance as opposed to the ties method. You should find this version having much better coding performance than Version 1, without any of the negative that merging has on the integrity of the model.
|
17 |
+
|
18 |
+
Prompt template: Alpaca
|
19 |
+
```
|
20 |
+
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
21 |
+
### Instruction:
|
22 |
+
{prompt}
|
23 |
+
### Response:
|
24 |
+
```
|
25 |
+
|
26 |
+
The models that were used in this merger were as follow:
|
27 |
+
|
28 |
+
- https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct
|
29 |
+
|
30 |
+
- https://huggingface.co/codefuse-ai/CodeFuse-DeepSeek-33B
|
31 |
+
|
32 |
+
- https://huggingface.co/WizardLM/WizardCoder-33B-V1.1
|
33 |
+
|
34 |
+
Thank you to the creators of the above ai models, they have full credit for the EveryoneLLM series of models. Without their hard work we wouldnt be able to achieve the great success we have in the open source community. 💗
|
35 |
+
|
36 |
+
You can find the write up for merging models here:
|
37 |
+
|
38 |
+
https://docs.google.com/document/d/1_vOftBnrk9NRk5h10UqrfJ5CDih9KBKL61yvrZtVWPE/edit?usp=sharing
|
39 |
+
|
40 |
+
Config for the merger can be found bellow:
|
41 |
+
```yaml
|
42 |
+
models:
|
43 |
+
- model: codefuse-ai_CodeFuse-DeepSeek-33B
|
44 |
+
parameters:
|
45 |
+
weight: 1
|
46 |
+
- model: deepseek-ai_deepseek-coder-33b-instruct
|
47 |
+
parameters:
|
48 |
+
weight: 1
|
49 |
+
- model: WizardLM_WizardCoder-33B-V1.1
|
50 |
+
parameters:
|
51 |
+
weight: 1
|
52 |
+
merge_method: task_arithmetic
|
53 |
+
base_model: deepseek-ai_deepseek-coder-33b-base
|
54 |
+
parameters:
|
55 |
+
normalize: true
|
56 |
+
int8_mask: true
|
57 |
+
dtype: float16
|
58 |
+
```
|
59 |
+
|