schroneko commited on
Commit
3fac8a5
·
verified ·
1 Parent(s): 01a80f7

Add files using upload-large-folder tool

Browse files
README.md ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ language:
5
+ - ja
6
+ - en
7
+ base_model: stockmark/Stockmark-2-100B-Instruct-beta
8
+ tags:
9
+ - mlx
10
+ ---
11
+
12
+ # mlx-community/Stockmark-2-100B-Instruct-beta-8bit
13
+
14
+ The Model [mlx-community/Stockmark-2-100B-Instruct-beta-8bit](https://huggingface.co/mlx-community/Stockmark-2-100B-Instruct-beta-8bit) was
15
+ converted to MLX format from [stockmark/Stockmark-2-100B-Instruct-beta](https://huggingface.co/stockmark/Stockmark-2-100B-Instruct-beta)
16
+ using mlx-lm version **0.21.5**.
17
+
18
+ ## Use with mlx
19
+
20
+ ```bash
21
+ pip install mlx-lm
22
+ ```
23
+
24
+ ```python
25
+ from mlx_lm import load, generate
26
+
27
+ model, tokenizer = load("mlx-community/Stockmark-2-100B-Instruct-beta-8bit")
28
+
29
+ prompt = "hello"
30
+
31
+ if tokenizer.chat_template is not None:
32
+ messages = [{"role": "user", "content": prompt}]
33
+ prompt = tokenizer.apply_chat_template(
34
+ messages, add_generation_prompt=True
35
+ )
36
+
37
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
38
+ ```
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 1,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 9216,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 32768,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 72,
18
+ "num_hidden_layers": 86,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 2,
21
+ "pretraining_tp": 1,
22
+ "quantization": {
23
+ "group_size": 64,
24
+ "bits": 8
25
+ },
26
+ "quantization_config": {
27
+ "group_size": 64,
28
+ "bits": 8
29
+ },
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_scaling": null,
32
+ "rope_theta": 10000,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.48.2",
36
+ "use_cache": true,
37
+ "vocab_size": 100352
38
+ }
model-00001-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e94942da655226695de22680aca885004e98c108af63a0a533488f368b9b62f0
3
+ size 5314435084
model-00002-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:881fd20f5d306172630f43bdcc8b7139ee6f14fb1214a03d8ec285af6165b325
3
+ size 5174132863
model-00003-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:446503f1183beafbe522376b58a955c85e4f6dafa5e27a9e0884f2282f7548c8
3
+ size 5294418885
model-00004-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ece2c8b6e19cce1af8456488def33d34156be773af23b51cce94d768558fa3e
3
+ size 5174132990
model-00005-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:424b148298be3f683cd7b507a866c43c3d1ff4e5e7694e64d2b5d9d9783cfb21
3
+ size 5294418951
model-00006-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60600295a8955205872e49e903574932896d95c9393c1474952094a5e2defaaa
3
+ size 5174132978
model-00007-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b21dec96052d721cf1112e0c1aeed8e8b011201ae46055d46dac30349d0adfc6
3
+ size 5294418949
model-00008-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9279bf9f42ffe2b2c4b5bf34d9d1f5fd11aca03b035f04191fbc194e80d620a
3
+ size 5174132942
model-00009-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc268c3548dedf01d36f8679daf76d05815aacc78427f9433f55942f25b8e243
3
+ size 5294418945
model-00010-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ffc0464f2ce8d6d024c4b748f14c25609479337db7c44e5fc0a4552193f761e
3
+ size 5174132946
model-00011-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8177676f0c83520c6f713aec9b5a4b0f01e52db764b4e96fe6a2e018e4227ec5
3
+ size 5294418921
model-00012-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26e96aac4fa05ac4a858d84d8d83d5eb9296495f4fdb2ffeff3358f6c665aac4
3
+ size 5174132966
model-00013-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e86cf36667c256fe8b6ff74dad59d64d6439bfc28c9a269287db647f4d7d932
3
+ size 5294418953
model-00014-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a8103bf3383cf49d3046f1323ae83913cfa3e92b7a9861f053da0a9f4dcb64e
3
+ size 5174132952
model-00015-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92c9e15213a28159ceb1b752315f1bf0c4859fcff812934be7adf5a4dd941124
3
+ size 5294418949
model-00016-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0584f830143592fdf327cbc0e6e5578a65cc793da4368bcce29789101117424
3
+ size 5174132958
model-00017-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf39d159d8db62f409c1be396f9d528175988e03e5a575957a3a9fb32debd16
3
+ size 5294418909
model-00018-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c26e09bb3c793e9b37d22ef0fbcf5f9620d2d1b5cc9dc8ee1e23522063968ad
3
+ size 5174132966
model-00019-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85eecb346c2856ba3be3b6a9917fb2cf5bdd94950c17b072ceb7ce05318fbab8
3
+ size 5294418963
model-00020-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:908e6fe819a0c5da499d21701243ea53521fca88fc49caa0c5625edb7dde1360
3
+ size 2466739685
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,212 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<pad>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<|system|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<|user|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<|assistant|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<|end|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<|reserved_special_token_0|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<|reserved_special_token_1|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "10": {
86
+ "content": "<|reserved_special_token_2|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "11": {
94
+ "content": "<|reserved_special_token_3|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "12": {
102
+ "content": "<|reserved_special_token_4|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "13": {
110
+ "content": "<|reserved_special_token_5|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "14": {
118
+ "content": "<|reserved_special_token_6|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "15": {
126
+ "content": "<|reserved_special_token_7|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "16": {
134
+ "content": "<|reserved_special_token_8|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "17": {
142
+ "content": "<|reserved_special_token_9|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "18": {
150
+ "content": "<|reserved_special_token_10|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "19": {
158
+ "content": "<|reserved_special_token_11|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "20": {
166
+ "content": "<|reserved_special_token_12|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "21": {
174
+ "content": "<|reserved_special_token_13|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "22": {
182
+ "content": "<|reserved_special_token_14|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "23": {
190
+ "content": "<|reserved_special_token_15|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ }
197
+ },
198
+ "bos_token": "<s>",
199
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + message['content'] + '<|end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}",
200
+ "clean_up_tokenization_spaces": false,
201
+ "eos_token": "</s>",
202
+ "extra_special_tokens": {},
203
+ "model_input_names": [
204
+ "input_ids",
205
+ "attention_mask"
206
+ ],
207
+ "model_max_length": 1000000000000000019884624838656,
208
+ "pad_token": "<pad>",
209
+ "padding_side": "left",
210
+ "tokenizer_class": "PreTrainedTokenizer",
211
+ "unk_token": "<unk>"
212
+ }