bartowski commited on
Commit
16c36c1
1 Parent(s): d7d1184

Llamacpp quants

Browse files
.gitattributes CHANGED
@@ -33,3 +33,29 @@ 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-instruct-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ granite-20b-code-instruct-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ granite-20b-code-instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ granite-20b-code-instruct-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ granite-20b-code-instruct-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
41
+ granite-20b-code-instruct-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
42
+ granite-20b-code-instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ granite-20b-code-instruct-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ granite-20b-code-instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
45
+ granite-20b-code-instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
46
+ granite-20b-code-instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
47
+ granite-20b-code-instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
48
+ granite-20b-code-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
49
+ granite-20b-code-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
50
+ granite-20b-code-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
51
+ granite-20b-code-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
52
+ granite-20b-code-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
53
+ granite-20b-code-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
54
+ granite-20b-code-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
55
+ granite-20b-code-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
56
+ granite-20b-code-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
57
+ granite-20b-code-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
58
+ granite-20b-code-instruct-f32.gguf/granite-20b-code-instruct-f32-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
59
+ granite-20b-code-instruct-f32.gguf/granite-20b-code-instruct-f32-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
60
+ granite-20b-code-instruct-f32.gguf/granite-20b-code-instruct-f32-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
61
+ granite-20b-code-instruct.imatrix filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,304 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: text-generation
3
+ base_model: ibm-granite/granite-20b-code-base
4
+ inference: true
5
+ license: apache-2.0
6
+ datasets:
7
+ - bigcode/commitpackft
8
+ - TIGER-Lab/MathInstruct
9
+ - meta-math/MetaMathQA
10
+ - glaiveai/glaive-code-assistant-v3
11
+ - glaive-function-calling-v2
12
+ - bugdaryan/sql-create-context-instruction
13
+ - garage-bAInd/Open-Platypus
14
+ - nvidia/HelpSteer
15
+ metrics:
16
+ - code_eval
17
+ library_name: transformers
18
+ tags:
19
+ - code
20
+ - granite
21
+ model-index:
22
+ - name: granite-20b-code-instruct
23
+ results:
24
+ - task:
25
+ type: text-generation
26
+ dataset:
27
+ type: bigcode/humanevalpack
28
+ name: HumanEvalSynthesis(Python)
29
+ metrics:
30
+ - name: pass@1
31
+ type: pass@1
32
+ value: 60.4
33
+ veriefied: false
34
+ - task:
35
+ type: text-generation
36
+ dataset:
37
+ type: bigcode/humanevalpack
38
+ name: HumanEvalSynthesis(JavaScript)
39
+ metrics:
40
+ - name: pass@1
41
+ type: pass@1
42
+ value: 53.7
43
+ veriefied: false
44
+ - task:
45
+ type: text-generation
46
+ dataset:
47
+ type: bigcode/humanevalpack
48
+ name: HumanEvalSynthesis(Java)
49
+ metrics:
50
+ - name: pass@1
51
+ type: pass@1
52
+ value: 58.5
53
+ veriefied: false
54
+ - task:
55
+ type: text-generation
56
+ dataset:
57
+ type: bigcode/humanevalpack
58
+ name: HumanEvalSynthesis(Go)
59
+ metrics:
60
+ - name: pass@1
61
+ type: pass@1
62
+ value: 42.1
63
+ veriefied: false
64
+ - task:
65
+ type: text-generation
66
+ dataset:
67
+ type: bigcode/humanevalpack
68
+ name: HumanEvalSynthesis(C++)
69
+ metrics:
70
+ - name: pass@1
71
+ type: pass@1
72
+ value: 45.7
73
+ veriefied: false
74
+ - task:
75
+ type: text-generation
76
+ dataset:
77
+ type: bigcode/humanevalpack
78
+ name: HumanEvalSynthesis(Rust)
79
+ metrics:
80
+ - name: pass@1
81
+ type: pass@1
82
+ value: 42.7
83
+ veriefied: false
84
+ - task:
85
+ type: text-generation
86
+ dataset:
87
+ type: bigcode/humanevalpack
88
+ name: HumanEvalExplain(Python)
89
+ metrics:
90
+ - name: pass@1
91
+ type: pass@1
92
+ value: 44.5
93
+ veriefied: false
94
+ - task:
95
+ type: text-generation
96
+ dataset:
97
+ type: bigcode/humanevalpack
98
+ name: HumanEvalExplain(JavaScript)
99
+ metrics:
100
+ - name: pass@1
101
+ type: pass@1
102
+ value: 42.7
103
+ veriefied: false
104
+ - task:
105
+ type: text-generation
106
+ dataset:
107
+ type: bigcode/humanevalpack
108
+ name: HumanEvalExplain(Java)
109
+ metrics:
110
+ - name: pass@1
111
+ type: pass@1
112
+ value: 49.4
113
+ veriefied: false
114
+ - task:
115
+ type: text-generation
116
+ dataset:
117
+ type: bigcode/humanevalpack
118
+ name: HumanEvalExplain(Go)
119
+ metrics:
120
+ - name: pass@1
121
+ type: pass@1
122
+ value: 32.3
123
+ veriefied: false
124
+ - task:
125
+ type: text-generation
126
+ dataset:
127
+ type: bigcode/humanevalpack
128
+ name: HumanEvalExplain(C++)
129
+ metrics:
130
+ - name: pass@1
131
+ type: pass@1
132
+ value: 42.1
133
+ veriefied: false
134
+ - task:
135
+ type: text-generation
136
+ dataset:
137
+ type: bigcode/humanevalpack
138
+ name: HumanEvalExplain(Rust)
139
+ metrics:
140
+ - name: pass@1
141
+ type: pass@1
142
+ value: 18.3
143
+ veriefied: false
144
+ - task:
145
+ type: text-generation
146
+ dataset:
147
+ type: bigcode/humanevalpack
148
+ name: HumanEvalFix(Python)
149
+ metrics:
150
+ - name: pass@1
151
+ type: pass@1
152
+ value: 43.9
153
+ veriefied: false
154
+ - task:
155
+ type: text-generation
156
+ dataset:
157
+ type: bigcode/humanevalpack
158
+ name: HumanEvalFix(JavaScript)
159
+ metrics:
160
+ - name: pass@1
161
+ type: pass@1
162
+ value: 43.9
163
+ veriefied: false
164
+ - task:
165
+ type: text-generation
166
+ dataset:
167
+ type: bigcode/humanevalpack
168
+ name: HumanEvalFix(Java)
169
+ metrics:
170
+ - name: pass@1
171
+ type: pass@1
172
+ value: 45.7
173
+ veriefied: false
174
+ - task:
175
+ type: text-generation
176
+ dataset:
177
+ type: bigcode/humanevalpack
178
+ name: HumanEvalFix(Go)
179
+ metrics:
180
+ - name: pass@1
181
+ type: pass@1
182
+ value: 41.5
183
+ veriefied: false
184
+ - task:
185
+ type: text-generation
186
+ dataset:
187
+ type: bigcode/humanevalpack
188
+ name: HumanEvalFix(C++)
189
+ metrics:
190
+ - name: pass@1
191
+ type: pass@1
192
+ value: 41.5
193
+ veriefied: false
194
+ - task:
195
+ type: text-generation
196
+ dataset:
197
+ type: bigcode/humanevalpack
198
+ name: HumanEvalFix(Rust)
199
+ metrics:
200
+ - name: pass@1
201
+ type: pass@1
202
+ value: 29.9
203
+ veriefied: false
204
+ quantized_by: bartowski
205
+ ---
206
+
207
+ ## Llamacpp imatrix Quantizations of granite-20b-code-instruct
208
+
209
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2940">b2940</a> for quantization.
210
+
211
+ Original model: https://huggingface.co/ibm-granite/granite-20b-code-instruct
212
+
213
+ All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/b6ac44691e994344625687afe3263b3a)
214
+
215
+ ## Prompt format
216
+
217
+ ```
218
+ System:
219
+ {system_prompt}
220
+
221
+ Question:
222
+ {prompt}
223
+
224
+ Answer:
225
+
226
+
227
+ Answer:
228
+
229
+ ```
230
+
231
+ ## Download a file (not the whole branch) from below:
232
+
233
+ | Filename | Quant type | File Size | Description |
234
+ | -------- | ---------- | --------- | ----------- |
235
+ | [granite-20b-code-instruct-Q8_0.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-Q8_0.gguf) | Q8_0 | 21.48GB | Extremely high quality, generally unneeded but max available quant. |
236
+ | [granite-20b-code-instruct-Q6_K.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-Q6_K.gguf) | Q6_K | 16.63GB | Very high quality, near perfect, *recommended*. |
237
+ | [granite-20b-code-instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-Q5_K_M.gguf) | Q5_K_M | 14.80GB | High quality, *recommended*. |
238
+ | [granite-20b-code-instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-Q5_K_S.gguf) | Q5_K_S | 14.01GB | High quality, *recommended*. |
239
+ | [granite-20b-code-instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-Q4_K_M.gguf) | Q4_K_M | 12.82GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
240
+ | [granite-20b-code-instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-Q4_K_S.gguf) | Q4_K_S | 11.66GB | Slightly lower quality with more space savings, *recommended*. |
241
+ | [granite-20b-code-instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-IQ4_NL.gguf) | IQ4_NL | 11.55GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
242
+ | [granite-20b-code-instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-IQ4_XS.gguf) | IQ4_XS | 10.93GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
243
+ | [granite-20b-code-instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-Q3_K_L.gguf) | Q3_K_L | 11.73GB | Lower quality but usable, good for low RAM availability. |
244
+ | [granite-20b-code-instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-Q3_K_M.gguf) | Q3_K_M | 10.56GB | Even lower quality. |
245
+ | [granite-20b-code-instruct-IQ3_M.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-IQ3_M.gguf) | IQ3_M | 9.58GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
246
+ | [granite-20b-code-instruct-IQ3_S.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-IQ3_S.gguf) | IQ3_S | 8.93GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
247
+ | [granite-20b-code-instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-Q3_K_S.gguf) | Q3_K_S | 8.93GB | Low quality, not recommended. |
248
+ | [granite-20b-code-instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-IQ3_XS.gguf) | IQ3_XS | 8.65GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
249
+ | [granite-20b-code-instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-IQ3_XXS.gguf) | IQ3_XXS | 8.06GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
250
+ | [granite-20b-code-instruct-Q2_K.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-Q2_K.gguf) | Q2_K | 7.92GB | Very low quality but surprisingly usable. |
251
+ | [granite-20b-code-instruct-IQ2_M.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-IQ2_M.gguf) | IQ2_M | 7.05GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
252
+ | [granite-20b-code-instruct-IQ2_S.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-IQ2_S.gguf) | IQ2_S | 6.52GB | Very low quality, uses SOTA techniques to be usable. |
253
+ | [granite-20b-code-instruct-IQ2_XS.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-IQ2_XS.gguf) | IQ2_XS | 6.15GB | Very low quality, uses SOTA techniques to be usable. |
254
+ | [granite-20b-code-instruct-IQ2_XXS.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-IQ2_XXS.gguf) | IQ2_XXS | 5.57GB | Lower quality, uses SOTA techniques to be usable. |
255
+ | [granite-20b-code-instruct-IQ1_M.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-IQ1_M.gguf) | IQ1_M | 4.91GB | Extremely low quality, *not* recommended. |
256
+ | [granite-20b-code-instruct-IQ1_S.gguf](https://huggingface.co/bartowski/granite-20b-code-instruct-GGUF/blob/main/granite-20b-code-instruct-IQ1_S.gguf) | IQ1_S | 4.51GB | Extremely low quality, *not* recommended. |
257
+
258
+ ## Downloading using huggingface-cli
259
+
260
+ First, make sure you have hugginface-cli installed:
261
+
262
+ ```
263
+ pip install -U "huggingface_hub[cli]"
264
+ ```
265
+
266
+ Then, you can target the specific file you want:
267
+
268
+ ```
269
+ huggingface-cli download bartowski/granite-20b-code-instruct-GGUF --include "granite-20b-code-instruct-Q4_K_M.gguf" --local-dir ./ --local-dir-use-symlinks False
270
+ ```
271
+
272
+ If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
273
+
274
+ ```
275
+ huggingface-cli download bartowski/granite-20b-code-instruct-GGUF --include "granite-20b-code-instruct-Q8_0.gguf/*" --local-dir granite-20b-code-instruct-Q8_0 --local-dir-use-symlinks False
276
+ ```
277
+
278
+ You can either specify a new local-dir (granite-20b-code-instruct-Q8_0) or download them all in place (./)
279
+
280
+ ## Which file should I choose?
281
+
282
+ A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
283
+
284
+ The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
285
+
286
+ If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
287
+
288
+ If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
289
+
290
+ Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
291
+
292
+ If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
293
+
294
+ If you want to get more into the weeds, you can check out this extremely useful feature chart:
295
+
296
+ [llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
297
+
298
+ But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
299
+
300
+ These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
301
+
302
+ The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
303
+
304
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
granite-20b-code-instruct-IQ1_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efd874065398abe5f6dfaf7deb19df2f58cdf7a17a79a4464659cf3cd4f7ff70
3
+ size 4912437280
granite-20b-code-instruct-IQ1_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d627d57a19fdf69c4e10c95a4116715f311c28b94167539db0a974f0d7e7cd9
3
+ size 4517697568
granite-20b-code-instruct-IQ2_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d63d3d559a67c01da6f6399f5872b1a6cce3ed2b79d33ba8f27dced2b5400ef
3
+ size 7052367904
granite-20b-code-instruct-IQ2_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9079659c0ffd7379f3ebcf1e0215cab132f326b548eba75007a3f0cfbdc9acdf
3
+ size 6526048288
granite-20b-code-instruct-IQ2_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972ddeaac457f9eb4adb0a47aaf971ecaedcfd72c9916cdc88e9f03145a936f7
3
+ size 6157998112
granite-20b-code-instruct-IQ2_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f6019f197583615dd49ce0ebea3c6276a0a4c398a8eb4990e64d03879b5fa2
3
+ size 5570336800
granite-20b-code-instruct-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3ce6d064a240a85f45caf33314c57bb566c40f8f49694e11e0e1505896dba05
3
+ size 9587185696
granite-20b-code-instruct-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e912a1586a5ab8a694155da28496b6c9b1aa1e8bd22bed1d911c06db8742b4d8
3
+ size 8934594592
granite-20b-code-instruct-IQ3_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:490a1cba9d1deb7e8c8321c08ec12e80df501170972cf0f93992df6a100c17e2
3
+ size 8658556960
granite-20b-code-instruct-IQ3_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638486004076eff7fdb863d76ed71268fae5761402b27727e9b06f9a65ddf20e
3
+ size 8062539808
granite-20b-code-instruct-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b6e44abf2b21742618f39d5de1003567080d290a8a5b9c53a7d0dd5eaedde7
3
+ size 11552479264
granite-20b-code-instruct-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8db7aec02cb64605b6878859768844e640fee6fce48b482db3b426a2ad03306e
3
+ size 10936506400
granite-20b-code-instruct-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee8162eecd611273452c337606bdb87d6357b9ad8707a4d3f10a86e779b2eef
3
+ size 7929485344
granite-20b-code-instruct-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a318a2477ecd17fc14358449ca4c224e9aadc7b68fe650c5e1df466dec6739
3
+ size 11736504352
granite-20b-code-instruct-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79631a1d50826d91636f80d1ddb5625deff7cab668a9ae597e395c88249e151d
3
+ size 10566293536
granite-20b-code-instruct-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cfbcfe61814a39fd4de6de9008cae7b6b579a1b119ac6ae9ca0d97a8a3920f1
3
+ size 8934594592
granite-20b-code-instruct-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97b657ab840801f8d5e30f2d47bf8320aa39b715e969e5552cec27d6f36a6bf1
3
+ size 12820207648
granite-20b-code-instruct-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b1b2603d3ac7b28edcc12d3a87d3c0d45cce2b5a33b166e822ea12fa228a69
3
+ size 11665725472
granite-20b-code-instruct-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3ceeb64f43ca534cf6ca1161c8a78e3087a7aa8416f6e545f58fac91a11115
3
+ size 14809339936
granite-20b-code-instruct-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afaf27118ec8a494e79b6c197dd79f089e408c3db28619a629b025f3ad83e8e5
3
+ size 14016370720
granite-20b-code-instruct-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d14451c99d633cac9f92e5dd578479d7b13b2ff9a8d57dcc4e615f25fca2fc3
3
+ size 16634255392
granite-20b-code-instruct-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d442229ed2c1cdcf4a779e36d76585858acd1564b24f2978acc1a6995d3eb6a
3
+ size 21481183264
granite-20b-code-instruct-f32.gguf/granite-20b-code-instruct-f32-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ccf14532df46cd6f02ea1663e830d13614a83e21de9031ef3b20e64fc2bced3
3
+ size 32049793248
granite-20b-code-instruct-f32.gguf/granite-20b-code-instruct-f32-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a69e3d8abf374dcb31daeabeab556dfe8d0e48a21906ef80db267f6852ec81d1
3
+ size 31846771616
granite-20b-code-instruct-f32.gguf/granite-20b-code-instruct-f32-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:297e6108fc746fadbebd52566ca433b7dc18132b0abb9dfa2d631c387dcef63d
3
+ size 16373162944
granite-20b-code-instruct.imatrix ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8887d0e9e29d401f449a6cdd7a780244f943fef9f0ff1b12b88e5d8140198eb
3
+ size 8952795