Hugging Face's logo

mlx-community
/
granite-34b-code-base-8bit

Text Generation
Transformers
Safetensors
MLX
gpt_bigcode
code
granite
Eval Results
text-generation-inference
Model card Files
xet
Community
1
prince-canuma commited on
Commit
a85cad3
·
verified ·
1 Parent(s): 28e277a

ed08854bc5effa1441504f82af5e7326a312159b0e0c81f21e0974833451244d

Browse files
Files changed (8) hide show
  1. README.md +115 -0
  2. config.json +32 -0
  3. merges.txt +0 -0
  4. model.safetensors.index.json +0 -0
  5. special_tokens_map.json +51 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +187 -0
  8. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: transformers
4
+ tags:
5
+ - code
6
+ - granite
7
+ - mlx
8
+ datasets:
9
+ - codeparrot/github-code-clean
10
+ - bigcode/starcoderdata
11
+ - open-web-math/open-web-math
12
+ - math-ai/StackMathQA
13
+ metrics:
14
+ - code_eval
15
+ pipeline_tag: text-generation
16
+ inference: true
17
+ model-index:
18
+ - name: granite-34b-code-base
19
+ results:
20
+ - task:
21
+ type: text-generation
22
+ dataset:
23
+ name: MBPP
24
+ type: mbpp
25
+ metrics:
26
+ - type: pass@1
27
+ value: 47.2
28
+ name: pass@1
29
+ - task:
30
+ type: text-generation
31
+ dataset:
32
+ name: MBPP+
33
+ type: evalplus/mbppplus
34
+ metrics:
35
+ - type: pass@1
36
+ value: 53.1
37
+ name: pass@1
38
+ - task:
39
+ type: text-generation
40
+ dataset:
41
+ name: HumanEvalSynthesis(Python)
42
+ type: bigcode/humanevalpack
43
+ metrics:
44
+ - type: pass@1
45
+ value: 48.2
46
+ name: pass@1
47
+ - type: pass@1
48
+ value: 54.9
49
+ name: pass@1
50
+ - type: pass@1
51
+ value: 61.6
52
+ name: pass@1
53
+ - type: pass@1
54
+ value: 40.2
55
+ name: pass@1
56
+ - type: pass@1
57
+ value: 50.0
58
+ name: pass@1
59
+ - type: pass@1
60
+ value: 39.6
61
+ name: pass@1
62
+ - type: pass@1
63
+ value: 42.7
64
+ name: pass@1
65
+ - type: pass@1
66
+ value: 26.2
67
+ name: pass@1
68
+ - type: pass@1
69
+ value: 47.0
70
+ name: pass@1
71
+ - type: pass@1
72
+ value: 26.8
73
+ name: pass@1
74
+ - type: pass@1
75
+ value: 36.6
76
+ name: pass@1
77
+ - type: pass@1
78
+ value: 25.0
79
+ name: pass@1
80
+ - type: pass@1
81
+ value: 20.1
82
+ name: pass@1
83
+ - type: pass@1
84
+ value: 30.5
85
+ name: pass@1
86
+ - type: pass@1
87
+ value: 40.9
88
+ name: pass@1
89
+ - type: pass@1
90
+ value: 34.1
91
+ name: pass@1
92
+ - type: pass@1
93
+ value: 39.0
94
+ name: pass@1
95
+ - type: pass@1
96
+ value: 12.2
97
+ name: pass@1
98
+ ---
99
+
100
+ # mlx-community/granite-34b-code-base-8bit
101
+
102
+ The Model [mlx-community/granite-34b-code-base-8bit](https://huggingface.co/mlx-community/granite-34b-code-base-8bit) was converted to MLX format from [ibm-granite/granite-34b-code-base](https://huggingface.co/ibm-granite/granite-34b-code-base) using mlx-lm version **0.13.0**.
103
+
104
+ ## Use with mlx
105
+
106
+ ```bash
107
+ pip install mlx-lm
108
+ ```
109
+
110
+ ```python
111
+ from mlx_lm import load, generate
112
+
113
+ model, tokenizer = load("mlx-community/granite-34b-code-base-8bit")
114
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
115
+ ```
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_pytorch_tanh",
3
+ "architectures": [
4
+ "GPTBigCodeForCausalLM"
5
+ ],
6
+ "attention_softmax_in_fp32": true,
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 0,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 0,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt_bigcode",
14
+ "multi_query": true,
15
+ "n_embd": 6144,
16
+ "n_head": 48,
17
+ "n_inner": 24576,
18
+ "n_layer": 88,
19
+ "n_positions": 8192,
20
+ "pad_token_id": 0,
21
+ "quantization": {
22
+ "group_size": 64,
23
+ "bits": 8
24
+ },
25
+ "resid_pdrop": 0.1,
26
+ "scale_attention_softmax_in_fp32": true,
27
+ "scale_attn_weights": true,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.38.1",
30
+ "use_cache": true,
31
+ "vocab_size": 49152
32
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
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 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "eos_token": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "pad_token": {
38
+ "content": "<|endoftext|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<|endoftext|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,187 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<filename>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<gh_stars>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<issue_start>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_comment>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_closed>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<jupyter_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_text>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_code>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_output>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<empty_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<commit_before>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<commit_msg>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "17": {
141
+ "content": "<commit_after>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "18": {
149
+ "content": "<reponame>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ }
156
+ },
157
+ "additional_special_tokens": [
158
+ "<|endoftext|>",
159
+ "<fim_prefix>",
160
+ "<fim_middle>",
161
+ "<fim_suffix>",
162
+ "<fim_pad>",
163
+ "<filename>",
164
+ "<gh_stars>",
165
+ "<issue_start>",
166
+ "<issue_comment>",
167
+ "<issue_closed>",
168
+ "<jupyter_start>",
169
+ "<jupyter_text>",
170
+ "<jupyter_code>",
171
+ "<jupyter_output>",
172
+ "<empty_output>",
173
+ "<commit_before>",
174
+ "<commit_msg>",
175
+ "<commit_after>",
176
+ "<reponame>"
177
+ ],
178
+ "bos_token": "<|endoftext|>",
179
+ "clean_up_tokenization_spaces": true,
180
+ "eos_token": "<|endoftext|>",
181
+ "model_max_length": 8192,
182
+ "pad_token": "<|endoftext|>",
183
+ "padding_side": "left",
184
+ "tokenizer_class": "GPT2Tokenizer",
185
+ "unk_token": "<|endoftext|>",
186
+ "vocab_size": 49152
187
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff