stelterlab commited on
Commit
ac0f040
1 Parent(s): 63f083a

Upload folder using huggingface_hub (#1)

Browse files

- 2f083a94c916a20b97ad37e90848cadcf489278de9f94f949b190ee317c296b5 (98b560ba8b2b17f74c00c952aaad76088d523da1)
- 79c8eb285d9744b0ec2318a004aed1ed0b01e2b395ccbd79985a48861203ce5b (a84a7d8d884a7e16fd347cd2530fcb1dea63c385)
- da0971fcaa67edc561f1673d2ddee68b907422a2550e79e33a6f9e770f9d32c3 (d29f501a331df56c778e6c3c6b5aa9de9731a7ad)
- 640485ff6f6f92d02a9af705e61bb376be0041266bbb7d810c972ab0ad133653 (5d032b5a8cc5499b6909c60247fa5baebb24a3b4)

.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 CHANGED
@@ -1,3 +1,138 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - de
4
+ - en
5
+ - it
6
+ - fr
7
+ - pt
8
+ - nl
9
+ - ar
10
+ - es
11
+ license: apache-2.0
12
+ tags:
13
+ - spectrum
14
+ - sft
15
+ - mlx
16
+ base_model: VAGOsolutions/SauerkrautLM-v2-14b-SFT
17
+ model-index:
18
+ - name: SauerkrautLM-v2-14b-SFT
19
+ results:
20
+ - task:
21
+ type: text-generation
22
+ name: Text Generation
23
+ dataset:
24
+ name: IFEval (0-Shot)
25
+ type: HuggingFaceH4/ifeval
26
+ args:
27
+ num_few_shot: 0
28
+ metrics:
29
+ - type: inst_level_strict_acc and prompt_level_strict_acc
30
+ value: 69.64
31
+ name: strict accuracy
32
+ source:
33
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-v2-14b-SFT
34
+ name: Open LLM Leaderboard
35
+ - task:
36
+ type: text-generation
37
+ name: Text Generation
38
+ dataset:
39
+ name: BBH (3-Shot)
40
+ type: BBH
41
+ args:
42
+ num_few_shot: 3
43
+ metrics:
44
+ - type: acc_norm
45
+ value: 45.82
46
+ name: normalized accuracy
47
+ source:
48
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-v2-14b-SFT
49
+ name: Open LLM Leaderboard
50
+ - task:
51
+ type: text-generation
52
+ name: Text Generation
53
+ dataset:
54
+ name: MATH Lvl 5 (4-Shot)
55
+ type: hendrycks/competition_math
56
+ args:
57
+ num_few_shot: 4
58
+ metrics:
59
+ - type: exact_match
60
+ value: 29.23
61
+ name: exact match
62
+ source:
63
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-v2-14b-SFT
64
+ name: Open LLM Leaderboard
65
+ - task:
66
+ type: text-generation
67
+ name: Text Generation
68
+ dataset:
69
+ name: GPQA (0-shot)
70
+ type: Idavidrein/gpqa
71
+ args:
72
+ num_few_shot: 0
73
+ metrics:
74
+ - type: acc_norm
75
+ value: 11.41
76
+ name: acc_norm
77
+ source:
78
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-v2-14b-SFT
79
+ name: Open LLM Leaderboard
80
+ - task:
81
+ type: text-generation
82
+ name: Text Generation
83
+ dataset:
84
+ name: MuSR (0-shot)
85
+ type: TAUR-Lab/MuSR
86
+ args:
87
+ num_few_shot: 0
88
+ metrics:
89
+ - type: acc_norm
90
+ value: 11.07
91
+ name: acc_norm
92
+ source:
93
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-v2-14b-SFT
94
+ name: Open LLM Leaderboard
95
+ - task:
96
+ type: text-generation
97
+ name: Text Generation
98
+ dataset:
99
+ name: MMLU-PRO (5-shot)
100
+ type: TIGER-Lab/MMLU-Pro
101
+ config: main
102
+ split: test
103
+ args:
104
+ num_few_shot: 5
105
+ metrics:
106
+ - type: acc
107
+ value: 46.73
108
+ name: accuracy
109
+ source:
110
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=VAGOsolutions/SauerkrautLM-v2-14b-SFT
111
+ name: Open LLM Leaderboard
112
+ ---
113
+
114
+ # stelterlab/SauerkrautLM-v2-14b-SFT-8bit
115
+
116
+ The Model [stelterlab/SauerkrautLM-v2-14b-SFT-8bit](https://huggingface.co/stelterlab/SauerkrautLM-v2-14b-SFT-8bit) was converted to MLX format from [VAGOsolutions/SauerkrautLM-v2-14b-SFT](https://huggingface.co/VAGOsolutions/SauerkrautLM-v2-14b-SFT) using mlx-lm version **0.19.2**.
117
+
118
+ ## Use with mlx
119
+
120
+ ```bash
121
+ pip install mlx-lm
122
+ ```
123
+
124
+ ```python
125
+ from mlx_lm import load, generate
126
+
127
+ model, tokenizer = load("stelterlab/SauerkrautLM-v2-14b-SFT-8bit")
128
+
129
+ prompt="hello"
130
+
131
+ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
132
+ messages = [{"role": "user", "content": prompt}]
133
+ prompt = tokenizer.apply_chat_template(
134
+ messages, tokenize=False, add_generation_prompt=True
135
+ )
136
+
137
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
138
+ ```
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "eos_token_id": 151645,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 5120,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 13824,
11
+ "max_position_embeddings": 32768,
12
+ "max_window_layers": 70,
13
+ "model_type": "qwen2",
14
+ "num_attention_heads": 40,
15
+ "num_hidden_layers": 48,
16
+ "num_key_value_heads": 8,
17
+ "quantization": {
18
+ "group_size": 64,
19
+ "bits": 8
20
+ },
21
+ "quantization_config": {
22
+ "group_size": 64,
23
+ "bits": 8
24
+ },
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_scaling": null,
27
+ "rope_theta": 1000000.0,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.45.2",
32
+ "use_cache": false,
33
+ "use_sliding_window": false,
34
+ "vocab_size": 152064
35
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7bb69edf0a105a73de341281e32438b904c2823bc1a903718f573462ac63f5d
3
+ size 5356676361
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da61d860add76196bec367300e95dbab7245707d9ed55b383dab0446ab150dc
3
+ size 5340062002
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d89b942c1c3f9cc466f0db4b408a82d2c9ff32c93fa37d785bc57de68d7edb51
3
+ size 4997352748
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 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff