LoneStriker
commited on
Commit
β’
7be46d2
1
Parent(s):
fb91cac
Upload folder using huggingface_hub
Browse files- .gitattributes +9 -35
- README.md +82 -0
- Synatra-Mixtral-8x7B-Q2_K.gguf +3 -0
- Synatra-Mixtral-8x7B-Q3_K_L.gguf +3 -0
- Synatra-Mixtral-8x7B-Q3_K_M.gguf +3 -0
- Synatra-Mixtral-8x7B-Q3_K_S.gguf +3 -0
- Synatra-Mixtral-8x7B-Q4_K_M.gguf +3 -0
- Synatra-Mixtral-8x7B-Q4_K_S.gguf +3 -0
- Synatra-Mixtral-8x7B-Q5_K_M.gguf +3 -0
- Synatra-Mixtral-8x7B-Q5_K_S.gguf +3 -0
- Synatra-Mixtral-8x7B-Q6_K.gguf +3 -0
- Synatra-Mixtral.png +0 -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 |
+
Synatra-Mixtral-8x7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
2 |
+
Synatra-Mixtral-8x7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
3 |
+
Synatra-Mixtral-8x7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
4 |
+
Synatra-Mixtral-8x7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
5 |
+
Synatra-Mixtral-8x7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
6 |
+
Synatra-Mixtral-8x7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
7 |
+
Synatra-Mixtral-8x7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
8 |
+
Synatra-Mixtral-8x7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
9 |
+
Synatra-Mixtral-8x7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
README.md
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- ko
|
5 |
+
- en
|
6 |
+
tags:
|
7 |
+
- moe
|
8 |
+
---
|
9 |
+
|
10 |
+
# **Synatra-Mixtral-8x7B**
|
11 |
+
<img src="./Synatra-Mixtral.png" alt="Synatra-Mixtral-8x7B" width="512"/>
|
12 |
+
|
13 |
+
|
14 |
+
**Synatra-Mixtral-8x7B** is a fine-tuned version of the Mixtral-8x7B-Instruct-v0.1 model using **Korean** datasets.
|
15 |
+
|
16 |
+
This model features overwhelmingly superior comprehension and inference capabilities and is licensed under apache-2.0.
|
17 |
+
|
18 |
+
# **Join Our Discord**
|
19 |
+
|
20 |
+
[Server Link](https://discord.gg/MrBt3PXdXc)
|
21 |
+
|
22 |
+
# **License**
|
23 |
+
|
24 |
+
**OPEN**, Apache-2.0.
|
25 |
+
|
26 |
+
# **Model Details**
|
27 |
+
|
28 |
+
**Base Model**
|
29 |
+
[mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
|
30 |
+
|
31 |
+
**Trained On**
|
32 |
+
A100 80GB * 6
|
33 |
+
|
34 |
+
**Instruction format**
|
35 |
+
|
36 |
+
It follows **Alpaca** format.
|
37 |
+
```
|
38 |
+
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
39 |
+
|
40 |
+
### Instruction:
|
41 |
+
{input}
|
42 |
+
|
43 |
+
### Response:
|
44 |
+
{output}
|
45 |
+
```
|
46 |
+
|
47 |
+
# **Model Benchmark**
|
48 |
+
TBD
|
49 |
+
|
50 |
+
# **Implementation Code**
|
51 |
+
|
52 |
+
```python
|
53 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
54 |
+
|
55 |
+
device = "cuda" # the device to load the model onto
|
56 |
+
|
57 |
+
model = AutoModelForCausalLM.from_pretrained("maywell/Synatra-Mixtral-8x7B")
|
58 |
+
tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-Mixtral-8x7B")
|
59 |
+
|
60 |
+
messages = [
|
61 |
+
{"role": "user", "content": "μμΈμνμΈμ μλμ±μ΄λ‘ μ λν΄μ μμΈν μ€λͺ
ν΄μ€."},
|
62 |
+
]
|
63 |
+
|
64 |
+
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
|
65 |
+
|
66 |
+
model_inputs = encodeds.to(device)
|
67 |
+
model.to(device)
|
68 |
+
|
69 |
+
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
|
70 |
+
decoded = tokenizer.batch_decode(generated_ids)
|
71 |
+
print(decoded[0])
|
72 |
+
```
|
73 |
+
|
74 |
+
# **Author's Message**
|
75 |
+
|
76 |
+
This model's training got sponsered by no one but support from people around Earth.
|
77 |
+
|
78 |
+
[Support Me](https://www.buymeacoffee.com/mwell)
|
79 |
+
|
80 |
+
Contact Me on Discord - **is.maywell**
|
81 |
+
|
82 |
+
Follow me on twitter: https://twitter.com/stablefluffy
|
Synatra-Mixtral-8x7B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d176eea59533dfccab36f158e0075654cd25f487868d2362b64ef6804e5ae84
|
3 |
+
size 17309173696
|
Synatra-Mixtral-8x7B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:267b5c90b6fc94acf375be74bab75303c3467924cf5fb2fe8066742008dd2424
|
3 |
+
size 24167589824
|
Synatra-Mixtral-8x7B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51ea22d3b91b4b6bc76369c63b550982989110d64c98cebf60730877140bbaec
|
3 |
+
size 22544394176
|
Synatra-Mixtral-8x7B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbbc23ad2397a4f020d39deeea7160e97efaedbf94969008168476c090329c49
|
3 |
+
size 20430464960
|
Synatra-Mixtral-8x7B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8888299ae1dd00c332576ade94bc9ff318ce72e8b97f926276ad28ae04c98cc3
|
3 |
+
size 28446410688
|
Synatra-Mixtral-8x7B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84738bdbd82279266d62f3ffeb90f2d049d48a64be6f3c5db00617677b2e282a
|
3 |
+
size 26743523264
|
Synatra-Mixtral-8x7B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01d92b8d527b4c43ef076443d8081f60a10e0449262a9f073124ccef5ebc24a0
|
3 |
+
size 33227524032
|
Synatra-Mixtral-8x7B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e34af82991f2c0d6f136a138c64d5b42b8bead580b6b2cbc88ca4528f2a05ff
|
3 |
+
size 32229279680
|
Synatra-Mixtral-8x7B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41f2e4dd7dd0179277c91fac345c370552e6c2e2e3c1ff6e8916fc33909157d9
|
3 |
+
size 38378760128
|
Synatra-Mixtral.png
ADDED