mayank-mishra commited on
Commit
d70433a
1 Parent(s): 6f2e22a
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. README.md +253 -0
  3. granite-20b-code-base.Q4_K_M.gguf +3 -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
+ granite-20b-code-base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,256 @@
1
  ---
 
 
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ pipeline_tag: text-generation
3
+ inference: true
4
  license: apache-2.0
5
+ datasets:
6
+ - codeparrot/github-code-clean
7
+ - bigcode/starcoderdata
8
+ # - Stackexchange
9
+ # - CommonCrawl
10
+ - open-web-math/open-web-math
11
+ - math-ai/StackMathQA
12
+ # - Arxiv
13
+ # - Wikipedia
14
+ # - conceptofmind/FLAN_2022 # Original link is broken, we used IBM's filtered version | Phase 2
15
+ metrics:
16
+ - code_eval
17
+ library_name: transformers
18
+ tags:
19
+ - code
20
+ - granite
21
+ model-index:
22
+ - name: granite-20b-code-base
23
+ results:
24
+ - task:
25
+ type: text-generation
26
+ dataset:
27
+ type: mbpp
28
+ name: MBPP
29
+ metrics:
30
+ - name: pass@1
31
+ type: pass@1
32
+ value: 43.8
33
+ veriefied: false
34
+ - task:
35
+ type: text-generation
36
+ dataset:
37
+ type: evalplus/mbppplus
38
+ name: MBPP+
39
+ metrics:
40
+ - name: pass@1
41
+ type: pass@1
42
+ value: 51.6
43
+ veriefied: false
44
+ - task:
45
+ type: text-generation
46
+ dataset:
47
+ type: bigcode/humanevalpack
48
+ name: HumanEvalSynthesis(Python)
49
+ metrics:
50
+ - name: pass@1
51
+ type: pass@1
52
+ value: 48.2
53
+ veriefied: false
54
+ - task:
55
+ type: text-generation
56
+ dataset:
57
+ type: bigcode/humanevalpack
58
+ name: HumanEvalSynthesis(JavaScript)
59
+ metrics:
60
+ - name: pass@1
61
+ type: pass@1
62
+ value: 50.0
63
+ veriefied: false
64
+ - task:
65
+ type: text-generation
66
+ dataset:
67
+ type: bigcode/humanevalpack
68
+ name: HumanEvalSynthesis(Java)
69
+ metrics:
70
+ - name: pass@1
71
+ type: pass@1
72
+ value: 59.1
73
+ veriefied: false
74
+ - task:
75
+ type: text-generation
76
+ dataset:
77
+ type: bigcode/humanevalpack
78
+ name: HumanEvalSynthesis(Go)
79
+ metrics:
80
+ - name: pass@1
81
+ type: pass@1
82
+ value: 32.3
83
+ veriefied: false
84
+ - task:
85
+ type: text-generation
86
+ dataset:
87
+ type: bigcode/humanevalpack
88
+ name: HumanEvalSynthesis(C++)
89
+ metrics:
90
+ - name: pass@1
91
+ type: pass@1
92
+ value: 40.9
93
+ veriefied: false
94
+ - task:
95
+ type: text-generation
96
+ dataset:
97
+ type: bigcode/humanevalpack
98
+ name: HumanEvalSynthesis(Rust)
99
+ metrics:
100
+ - name: pass@1
101
+ type: pass@1
102
+ value: 35.4
103
+ veriefied: false
104
+ - task:
105
+ type: text-generation
106
+ dataset:
107
+ type: bigcode/humanevalpack
108
+ name: HumanEvalExplain(Python)
109
+ metrics:
110
+ - name: pass@1
111
+ type: pass@1
112
+ value: 17.1
113
+ veriefied: false
114
+ - task:
115
+ type: text-generation
116
+ dataset:
117
+ type: bigcode/humanevalpack
118
+ name: HumanEvalExplain(JavaScript)
119
+ metrics:
120
+ - name: pass@1
121
+ type: pass@1
122
+ value: 18.3
123
+ veriefied: false
124
+ - task:
125
+ type: text-generation
126
+ dataset:
127
+ type: bigcode/humanevalpack
128
+ name: HumanEvalExplain(Java)
129
+ metrics:
130
+ - name: pass@1
131
+ type: pass@1
132
+ value: 23.2
133
+ veriefied: false
134
+ - task:
135
+ type: text-generation
136
+ dataset:
137
+ type: bigcode/humanevalpack
138
+ name: HumanEvalExplain(Go)
139
+ metrics:
140
+ - name: pass@1
141
+ type: pass@1
142
+ value: 10.4
143
+ veriefied: false
144
+ - task:
145
+ type: text-generation
146
+ dataset:
147
+ type: bigcode/humanevalpack
148
+ name: HumanEvalExplain(C++)
149
+ metrics:
150
+ - name: pass@1
151
+ type: pass@1
152
+ value: 25.6
153
+ veriefied: false
154
+ - task:
155
+ type: text-generation
156
+ dataset:
157
+ type: bigcode/humanevalpack
158
+ name: HumanEvalExplain(Rust)
159
+ metrics:
160
+ - name: pass@1
161
+ type: pass@1
162
+ value: 18.3
163
+ veriefied: false
164
+ - task:
165
+ type: text-generation
166
+ dataset:
167
+ type: bigcode/humanevalpack
168
+ name: HumanEvalFix(Python)
169
+ metrics:
170
+ - name: pass@1
171
+ type: pass@1
172
+ value: 23.2
173
+ veriefied: false
174
+ - task:
175
+ type: text-generation
176
+ dataset:
177
+ type: bigcode/humanevalpack
178
+ name: HumanEvalFix(JavaScript)
179
+ metrics:
180
+ - name: pass@1
181
+ type: pass@1
182
+ value: 23.8
183
+ veriefied: false # Check
184
+ - task:
185
+ type: text-generation
186
+ dataset:
187
+ type: bigcode/humanevalpack
188
+ name: HumanEvalFix(Java)
189
+ metrics:
190
+ - name: pass@1
191
+ type: pass@1
192
+ value: 14.6
193
+ veriefied: false
194
+ - task:
195
+ type: text-generation
196
+ dataset:
197
+ type: bigcode/humanevalpack
198
+ name: HumanEvalFix(Go)
199
+ metrics:
200
+ - name: pass@1
201
+ type: pass@1
202
+ value: 26.2
203
+ veriefied: false
204
+ - task:
205
+ type: text-generation
206
+ dataset:
207
+ type: bigcode/humanevalpack
208
+ name: HumanEvalFix(C++)
209
+ metrics:
210
+ - name: pass@1
211
+ type: pass@1
212
+ value: 15.2
213
+ veriefied: false
214
+ - task:
215
+ type: text-generation
216
+ dataset:
217
+ type: bigcode/humanevalpack
218
+ name: HumanEvalFix(Rust)
219
+ metrics:
220
+ - name: pass@1
221
+ type: pass@1
222
+ value: 3.0
223
+ veriefied: false
224
  ---
225
+
226
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png)
227
+
228
+ # ibm-granite/granite-20b-code-base-Q4_K_M-GGUF
229
+ This model was converted to GGUF format from [`ibm-granite/granite-20b-code-base`](https://huggingface.co/ibm-granite/granite-20b-code-base).
230
+ Refer to the [original model card](https://huggingface.co/ibm-granite/granite-20b-code-base) for more details on the model.
231
+ ## Use with llama.cpp
232
+
233
+ Install llama.cpp through brew.
234
+
235
+ ```bash
236
+ brew install ggerganov/ggerganov/llama.cpp
237
+ ```
238
+ Invoke the llama.cpp server or the CLI.
239
+
240
+ CLI:
241
+
242
+ ```bash
243
+ llama-cli --hf-repo ibm-granite/granite-20b-code-base-Q4_K_M-GGUF --model granite-20b-code-base.Q4_K_M.gguf -p "def generate(random_seed: int):"
244
+ ```
245
+
246
+ Server:
247
+
248
+ ```bash
249
+ llama-server --hf-repo ibm-granite/granite-20b-code-base-Q4_K_M-GGUF --model granite-20b-code-base.Q4_K_M.gguf -c 2048
250
+ ```
251
+
252
+ Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
253
+
254
+ ```
255
+ git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m granite-20b-code-base.Q4_K_M.gguf -n 128
256
+ ```
granite-20b-code-base.Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f85769a9438b4f7a42377223aa0fbfc4cedc3e2e142259243ba73730d816dc7a
3
+ size 12820206944