Transformers
GGUF
TensorBlock
GGUF
Eval Results
Inference Endpoints
conversational
morriszms commited on
Commit
b1308be
1 Parent(s): 527f3b1

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,15 @@ 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
+ ConfigurableHermes-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ ConfigurableHermes-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ ConfigurableHermes-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ ConfigurableHermes-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ ConfigurableHermes-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ ConfigurableHermes-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ ConfigurableHermes-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ ConfigurableHermes-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ ConfigurableHermes-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ ConfigurableHermes-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ ConfigurableHermes-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ ConfigurableHermes-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
ConfigurableHermes-7B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1cae9842395d956f0064f96d50c754a2a8ce0ba50a4a6729b2e9b3687c89992
3
+ size 2719252032
ConfigurableHermes-7B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d7167f09f772f71136dee19ddbf3f7867c784d9079aa6dc7d6669b69443263b
3
+ size 3822035328
ConfigurableHermes-7B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c23fed39b723589dc0f62743a1f8bdc85c53ac0d55dbb309f61bd006f0520528
3
+ size 3518996864
ConfigurableHermes-7B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63dce1ed1059b90b14b648c746e669fa4b8765b14c9da3df1188327a24f0bb21
3
+ size 3164578176
ConfigurableHermes-7B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d059a811de151d63c9eef0f9595928e7c7e882e89f536946d5cdd742c80c8422
3
+ size 4108928448
ConfigurableHermes-7B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf05ab5aed11c1b66fe421332d2bc5b416267bbfe624af68c1642bda31e402d2
3
+ size 4368451008
ConfigurableHermes-7B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90acacafca25d600778752ebd2f5bdd6d8b115285bd22262a88b4a92d5503b69
3
+ size 4140385728
ConfigurableHermes-7B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d763ca305117acfa91231ebec12d04cbe8aec854076fb705dc331bbcf449d59b
3
+ size 4997728704
ConfigurableHermes-7B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71f602e4a6ca4f79124f0f1fa7af4e97d5b90835a324db461244d826cbda6c5a
3
+ size 5131422144
ConfigurableHermes-7B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:960433a39574c295a4ae19e0492d0520bfcedb72128fb392ed4e59146aa50169
3
+ size 4997728704
ConfigurableHermes-7B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bf01bb25f840f6d753a4bf5d1e4ab114ca35bbc05e7c837970ffc0b36919ad6
3
+ size 5942078976
ConfigurableHermes-7B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98711c68f7f29b1091021558338f1ce8dd25ed91cb59c1f877050c5746c41d1a
3
+ size 7695875456
README.md ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: transformers
4
+ datasets:
5
+ - vicgalle/configurable-system-prompt-multitask
6
+ tags:
7
+ - TensorBlock
8
+ - GGUF
9
+ base_model: vicgalle/ConfigurableHermes-7B
10
+ model-index:
11
+ - name: ConfigurableHermes-7B
12
+ results:
13
+ - task:
14
+ type: text-generation
15
+ name: Text Generation
16
+ dataset:
17
+ name: AI2 Reasoning Challenge (25-Shot)
18
+ type: ai2_arc
19
+ config: ARC-Challenge
20
+ split: test
21
+ args:
22
+ num_few_shot: 25
23
+ metrics:
24
+ - type: acc_norm
25
+ value: 66.04
26
+ name: normalized accuracy
27
+ source:
28
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
29
+ name: Open LLM Leaderboard
30
+ - task:
31
+ type: text-generation
32
+ name: Text Generation
33
+ dataset:
34
+ name: HellaSwag (10-Shot)
35
+ type: hellaswag
36
+ split: validation
37
+ args:
38
+ num_few_shot: 10
39
+ metrics:
40
+ - type: acc_norm
41
+ value: 84.31
42
+ name: normalized accuracy
43
+ source:
44
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
45
+ name: Open LLM Leaderboard
46
+ - task:
47
+ type: text-generation
48
+ name: Text Generation
49
+ dataset:
50
+ name: MMLU (5-Shot)
51
+ type: cais/mmlu
52
+ config: all
53
+ split: test
54
+ args:
55
+ num_few_shot: 5
56
+ metrics:
57
+ - type: acc
58
+ value: 62.44
59
+ name: accuracy
60
+ source:
61
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
62
+ name: Open LLM Leaderboard
63
+ - task:
64
+ type: text-generation
65
+ name: Text Generation
66
+ dataset:
67
+ name: TruthfulQA (0-shot)
68
+ type: truthful_qa
69
+ config: multiple_choice
70
+ split: validation
71
+ args:
72
+ num_few_shot: 0
73
+ metrics:
74
+ - type: mc2
75
+ value: 61.71
76
+ source:
77
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
78
+ name: Open LLM Leaderboard
79
+ - task:
80
+ type: text-generation
81
+ name: Text Generation
82
+ dataset:
83
+ name: Winogrande (5-shot)
84
+ type: winogrande
85
+ config: winogrande_xl
86
+ split: validation
87
+ args:
88
+ num_few_shot: 5
89
+ metrics:
90
+ - type: acc
91
+ value: 77.43
92
+ name: accuracy
93
+ source:
94
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
95
+ name: Open LLM Leaderboard
96
+ - task:
97
+ type: text-generation
98
+ name: Text Generation
99
+ dataset:
100
+ name: GSM8k (5-shot)
101
+ type: gsm8k
102
+ config: main
103
+ split: test
104
+ args:
105
+ num_few_shot: 5
106
+ metrics:
107
+ - type: acc
108
+ value: 61.41
109
+ name: accuracy
110
+ source:
111
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
112
+ name: Open LLM Leaderboard
113
+ - task:
114
+ type: text-generation
115
+ name: Text Generation
116
+ dataset:
117
+ name: IFEval (0-Shot)
118
+ type: HuggingFaceH4/ifeval
119
+ args:
120
+ num_few_shot: 0
121
+ metrics:
122
+ - type: inst_level_strict_acc and prompt_level_strict_acc
123
+ value: 54.11
124
+ name: strict accuracy
125
+ source:
126
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
127
+ name: Open LLM Leaderboard
128
+ - task:
129
+ type: text-generation
130
+ name: Text Generation
131
+ dataset:
132
+ name: BBH (3-Shot)
133
+ type: BBH
134
+ args:
135
+ num_few_shot: 3
136
+ metrics:
137
+ - type: acc_norm
138
+ value: 23.16
139
+ name: normalized accuracy
140
+ source:
141
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
142
+ name: Open LLM Leaderboard
143
+ - task:
144
+ type: text-generation
145
+ name: Text Generation
146
+ dataset:
147
+ name: MATH Lvl 5 (4-Shot)
148
+ type: hendrycks/competition_math
149
+ args:
150
+ num_few_shot: 4
151
+ metrics:
152
+ - type: exact_match
153
+ value: 4.31
154
+ name: exact match
155
+ source:
156
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
157
+ name: Open LLM Leaderboard
158
+ - task:
159
+ type: text-generation
160
+ name: Text Generation
161
+ dataset:
162
+ name: GPQA (0-shot)
163
+ type: Idavidrein/gpqa
164
+ args:
165
+ num_few_shot: 0
166
+ metrics:
167
+ - type: acc_norm
168
+ value: 3.58
169
+ name: acc_norm
170
+ source:
171
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
172
+ name: Open LLM Leaderboard
173
+ - task:
174
+ type: text-generation
175
+ name: Text Generation
176
+ dataset:
177
+ name: MuSR (0-shot)
178
+ type: TAUR-Lab/MuSR
179
+ args:
180
+ num_few_shot: 0
181
+ metrics:
182
+ - type: acc_norm
183
+ value: 9.11
184
+ name: acc_norm
185
+ source:
186
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
187
+ name: Open LLM Leaderboard
188
+ - task:
189
+ type: text-generation
190
+ name: Text Generation
191
+ dataset:
192
+ name: MMLU-PRO (5-shot)
193
+ type: TIGER-Lab/MMLU-Pro
194
+ config: main
195
+ split: test
196
+ args:
197
+ num_few_shot: 5
198
+ metrics:
199
+ - type: acc
200
+ value: 22.5
201
+ name: accuracy
202
+ source:
203
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B
204
+ name: Open LLM Leaderboard
205
+ ---
206
+
207
+ <div style="width: auto; margin-left: auto; margin-right: auto">
208
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
209
+ </div>
210
+ <div style="display: flex; justify-content: space-between; width: 100%;">
211
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
212
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
213
+ Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
214
+ </p>
215
+ </div>
216
+ </div>
217
+
218
+ ## vicgalle/ConfigurableHermes-7B - GGUF
219
+
220
+ This repo contains GGUF format model files for [vicgalle/ConfigurableHermes-7B](https://huggingface.co/vicgalle/ConfigurableHermes-7B).
221
+
222
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
223
+
224
+ ## Prompt template
225
+
226
+ ```
227
+ <|im_start|>system
228
+ {system_prompt}<|im_end|>
229
+ <|im_start|>user
230
+ {prompt}<|im_end|>
231
+ <|im_start|>assistant
232
+ ```
233
+
234
+ ## Model file specification
235
+
236
+ | Filename | Quant type | File Size | Description |
237
+ | -------- | ---------- | --------- | ----------- |
238
+ | [ConfigurableHermes-7B-Q2_K.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/tree/main/ConfigurableHermes-7B-Q2_K.gguf) | Q2_K | 2.533 GB | smallest, significant quality loss - not recommended for most purposes |
239
+ | [ConfigurableHermes-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/tree/main/ConfigurableHermes-7B-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
240
+ | [ConfigurableHermes-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/tree/main/ConfigurableHermes-7B-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
241
+ | [ConfigurableHermes-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/tree/main/ConfigurableHermes-7B-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
242
+ | [ConfigurableHermes-7B-Q4_0.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/tree/main/ConfigurableHermes-7B-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
243
+ | [ConfigurableHermes-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/tree/main/ConfigurableHermes-7B-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
244
+ | [ConfigurableHermes-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/tree/main/ConfigurableHermes-7B-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
245
+ | [ConfigurableHermes-7B-Q5_0.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/tree/main/ConfigurableHermes-7B-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
246
+ | [ConfigurableHermes-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/tree/main/ConfigurableHermes-7B-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
247
+ | [ConfigurableHermes-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/tree/main/ConfigurableHermes-7B-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
248
+ | [ConfigurableHermes-7B-Q6_K.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/tree/main/ConfigurableHermes-7B-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
249
+ | [ConfigurableHermes-7B-Q8_0.gguf](https://huggingface.co/tensorblock/ConfigurableHermes-7B-GGUF/tree/main/ConfigurableHermes-7B-Q8_0.gguf) | Q8_0 | 7.167 GB | very large, extremely low quality loss - not recommended |
250
+
251
+
252
+ ## Downloading instruction
253
+
254
+ ### Command line
255
+
256
+ Firstly, install Huggingface Client
257
+
258
+ ```shell
259
+ pip install -U "huggingface_hub[cli]"
260
+ ```
261
+
262
+ Then, downoad the individual model file the a local directory
263
+
264
+ ```shell
265
+ huggingface-cli download tensorblock/ConfigurableHermes-7B-GGUF --include "ConfigurableHermes-7B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
266
+ ```
267
+
268
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
269
+
270
+ ```shell
271
+ huggingface-cli download tensorblock/ConfigurableHermes-7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
272
+ ```