Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +41 -0
- added_tokens.json +18 -0
- config.json +0 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model-00001-of-00017.safetensors +3 -0
- model-00002-of-00017.safetensors +3 -0
- model-00003-of-00017.safetensors +3 -0
- model-00004-of-00017.safetensors +3 -0
- model-00005-of-00017.safetensors +3 -0
- model-00006-of-00017.safetensors +3 -0
- model-00007-of-00017.safetensors +3 -0
- model-00008-of-00017.safetensors +3 -0
- model-00009-of-00017.safetensors +3 -0
- model-00010-of-00017.safetensors +3 -0
- model-00011-of-00017.safetensors +3 -0
- model-00012-of-00017.safetensors +3 -0
- model-00013-of-00017.safetensors +3 -0
- model-00014-of-00017.safetensors +3 -0
- model-00015-of-00017.safetensors +3 -0
- model-00016-of-00017.safetensors +3 -0
- model-00017-of-00017.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +33 -0
- tokenizer.json +3 -0
- tokenizer_config.json +161 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* 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
|
|
|
|
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
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
license_link: https://huggingface.co/rednote-hilab/dots.llm1.inst/blob/main/LICENSE
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
base_model: rednote-hilab/dots.llm1.inst
|
6 |
+
tags:
|
7 |
+
- chat
|
8 |
+
- mlx
|
9 |
+
library_name: mlx
|
10 |
+
language:
|
11 |
+
- en
|
12 |
+
- zh
|
13 |
+
---
|
14 |
+
|
15 |
+
# mlx-community/dots.llm1.inst-mixed-4-6bit
|
16 |
+
|
17 |
+
This model [mlx-community/dots.llm1.inst-mixed-4-6bit](https://huggingface.co/mlx-community/dots.llm1.inst-mixed-4-6bit) was
|
18 |
+
converted to MLX format from [rednote-hilab/dots.llm1.inst](https://huggingface.co/rednote-hilab/dots.llm1.inst)
|
19 |
+
using mlx-lm version **0.25.3**.
|
20 |
+
|
21 |
+
## Use with mlx
|
22 |
+
|
23 |
+
```bash
|
24 |
+
pip install mlx-lm
|
25 |
+
```
|
26 |
+
|
27 |
+
```python
|
28 |
+
from mlx_lm import load, generate
|
29 |
+
|
30 |
+
model, tokenizer = load("mlx-community/dots.llm1.inst-mixed-4-6bit")
|
31 |
+
|
32 |
+
prompt = "hello"
|
33 |
+
|
34 |
+
if tokenizer.chat_template is not None:
|
35 |
+
messages = [{"role": "user", "content": prompt}]
|
36 |
+
prompt = tokenizer.apply_chat_template(
|
37 |
+
messages, add_generation_prompt=True
|
38 |
+
)
|
39 |
+
|
40 |
+
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
41 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endofexecution|>": 151655,
|
3 |
+
"<|endofobservation|>": 151653,
|
4 |
+
"<|endofresponse|>": 151649,
|
5 |
+
"<|endofsystem|>": 151651,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|endofuserprompt|>": 151647,
|
8 |
+
"<|execution|>": 151654,
|
9 |
+
"<|im_end|>": 151645,
|
10 |
+
"<|im_start|>": 151644,
|
11 |
+
"<|observation|>": 151652,
|
12 |
+
"<|reject-unknown|>": 151656,
|
13 |
+
"<|response|>": 151648,
|
14 |
+
"<|sec-cot|>": 151657,
|
15 |
+
"<|sec-end-cot|>": 151658,
|
16 |
+
"<|system|>": 151650,
|
17 |
+
"<|userprompt|>": 151646
|
18 |
+
}
|
config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"do_sample": true,
|
4 |
+
"temperature": 0.7,
|
5 |
+
"top_p": 0.8,
|
6 |
+
"bos_token_id": 151643,
|
7 |
+
"eos_token_id": [
|
8 |
+
151643,
|
9 |
+
151649
|
10 |
+
],
|
11 |
+
"transformers_version": "4.46.3"
|
12 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76e8d751d5d0418f184950f53665ab568c9d6b60e52affda5fbf18113f2751c6
|
3 |
+
size 5007970758
|
model-00002-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fac4ae963cd41f7ffc5285cd91ff7a9816af2163b6b42a0c9e2de458032b21e1
|
3 |
+
size 5313134128
|
model-00003-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d604596e5f5ba79563e6339984e9112866ee5e3900c66a47573ee00bad82a595
|
3 |
+
size 5361454626
|
model-00004-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:549705ef00e16e31ae87f8cf23f29fe1e15e0bc4a3508ba11a960bcaf4261abd
|
3 |
+
size 5042687795
|
model-00005-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e61c3f1302c16c28a1e05236d56a95788c884c811ae62f9da387fdaf007c1517
|
3 |
+
size 5179788805
|
model-00006-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f871583a1bf60c8d908b76bc8254e0d8cb41a73b4f83110836cc441579135a9c
|
3 |
+
size 5363336429
|
model-00007-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5995f7281fadcd3d98a57908651f1926df6f292bfab218dbb20ca547d017e652
|
3 |
+
size 5347428844
|
model-00008-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8be20dcd5ac22f1aa5f297413a981a776ef23b9739e2511b2560dfce0fd04dd
|
3 |
+
size 5042687769
|
model-00009-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:996902c52336302d19125c44afb05b27dc3bbddb4e20e8e34ed438878fd39ab6
|
3 |
+
size 5179788905
|
model-00010-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6f8903e378342389960852853e8531cb2b5ddaff4f697fb4ac25f8fb4f0ab36
|
3 |
+
size 5361454716
|
model-00011-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c3c846ef300fe94651a3a94fa49181741463fd1cb5e1621d5098cf7da3434aa
|
3 |
+
size 5042687765
|
model-00012-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f34532b987aaf0b63d645c8fe6c5a2d65bc2bd78c15dfcfb924082cb33d7b16f
|
3 |
+
size 4934074034
|
model-00013-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:413dbfd60efa1f72d10a80feb7209c01e8b24bfb607bebc140938b47fcde3187
|
3 |
+
size 5179788849
|
model-00014-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff854054ea54460f2e501e6bf9867ec038489c0df6e23c62ac3eca785568f84a
|
3 |
+
size 5361454738
|
model-00015-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f37fe9088c856a722f941b1ed76ce2b0f5c99e271a5f2fa7850bfcb1a2cbfeb4
|
3 |
+
size 5368120074
|
model-00016-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7aef719278ef6d78415e934b031f3c7122a26155c8642cfe3b2e8944d59be51a
|
3 |
+
size 5352082038
|
model-00017-of-00017.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e7e7da6f7282ec4df4b4866d59f7242ff86c9415000f3eefc36772bdacbff38
|
3 |
+
size 2647965319
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|userprompt|>",
|
6 |
+
"<|endofuserprompt|>",
|
7 |
+
"<|response|>",
|
8 |
+
"<|endofresponse|>",
|
9 |
+
"<|system|>",
|
10 |
+
"<|endofsystem|>",
|
11 |
+
"<|observation|>",
|
12 |
+
"<|endofobservation|>",
|
13 |
+
"<|execution|>",
|
14 |
+
"<|endofexecution|>",
|
15 |
+
"<|reject-unknown|>",
|
16 |
+
"<|sec-cot|>",
|
17 |
+
"<|sec-end-cot|>"
|
18 |
+
],
|
19 |
+
"eos_token": {
|
20 |
+
"content": "<|endofresponse|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
+
"pad_token": {
|
27 |
+
"content": "<|endofresponse|>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": false,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe750f7b1f42fb8f760ee7ee91fa5fb3974795b3dc14c269819b83a086f5e98d
|
3 |
+
size 11420764
|
tokenizer_config.json
ADDED
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"151646": {
|
29 |
+
"content": "<|userprompt|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"151647": {
|
37 |
+
"content": "<|endofuserprompt|>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"151648": {
|
45 |
+
"content": "<|response|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"151649": {
|
53 |
+
"content": "<|endofresponse|>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"151650": {
|
61 |
+
"content": "<|system|>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"151651": {
|
69 |
+
"content": "<|endofsystem|>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"151652": {
|
77 |
+
"content": "<|observation|>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"151653": {
|
85 |
+
"content": "<|endofobservation|>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"151654": {
|
93 |
+
"content": "<|execution|>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"151655": {
|
101 |
+
"content": "<|endofexecution|>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"151656": {
|
109 |
+
"content": "<|reject-unknown|>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"151657": {
|
117 |
+
"content": "<|sec-cot|>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"151658": {
|
125 |
+
"content": "<|sec-end-cot|>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
}
|
132 |
+
},
|
133 |
+
"additional_special_tokens": [
|
134 |
+
"<|im_start|>",
|
135 |
+
"<|im_end|>",
|
136 |
+
"<|userprompt|>",
|
137 |
+
"<|endofuserprompt|>",
|
138 |
+
"<|response|>",
|
139 |
+
"<|endofresponse|>",
|
140 |
+
"<|system|>",
|
141 |
+
"<|endofsystem|>",
|
142 |
+
"<|observation|>",
|
143 |
+
"<|endofobservation|>",
|
144 |
+
"<|execution|>",
|
145 |
+
"<|endofexecution|>",
|
146 |
+
"<|reject-unknown|>",
|
147 |
+
"<|sec-cot|>",
|
148 |
+
"<|sec-end-cot|>"
|
149 |
+
],
|
150 |
+
"bos_token": null,
|
151 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}<|system|>{{ messages[0]['content'] }}<|endofsystem|>{% set start_idx = 1 %}{% else %}<|system|>You are a helpful assistant.<|endofsystem|>{% set start_idx = 0 %}{% endif %}{% for idx in range(start_idx, messages|length) %}{% if messages[idx]['role'] == 'user' %}<|userprompt|>{{ messages[idx]['content'] }}<|endofuserprompt|>{% elif messages[idx]['role'] == 'assistant' %}<|response|>{{ messages[idx]['content'] }}<|endofresponse|>{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] == 'user' %}<|response|>{% endif %}",
|
152 |
+
"clean_up_tokenization_spaces": false,
|
153 |
+
"eos_token": "<|endofresponse|>",
|
154 |
+
"errors": "replace",
|
155 |
+
"extra_special_tokens": {},
|
156 |
+
"model_max_length": 131072,
|
157 |
+
"pad_token": "<|endofresponse|>",
|
158 |
+
"split_special_tokens": false,
|
159 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
160 |
+
"unk_token": null
|
161 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|