morriszms commited on
Commit
9b1643c
1 Parent(s): e45b1f0

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
+ Bagel-Hermes-34B-Slerp-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Bagel-Hermes-34B-Slerp-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Bagel-Hermes-34B-Slerp-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Bagel-Hermes-34B-Slerp-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Bagel-Hermes-34B-Slerp-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Bagel-Hermes-34B-Slerp-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Bagel-Hermes-34B-Slerp-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Bagel-Hermes-34B-Slerp-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Bagel-Hermes-34B-Slerp-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Bagel-Hermes-34B-Slerp-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Bagel-Hermes-34B-Slerp-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Bagel-Hermes-34B-Slerp-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Bagel-Hermes-34B-Slerp-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b8e918b42747740867ff67cefd82dd356ae9e8d349df6cbc925adeb37327cfa
3
+ size 12825250944
Bagel-Hermes-34B-Slerp-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41edd2bc36efc44b61b0d6b9af5043718b2ab458779ff16e5aacca18bd07c74d
3
+ size 18139464256
Bagel-Hermes-34B-Slerp-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65f2c0ca58a4a8cef8141c8ea611db64a9be4a14b0ef546af8bb9518afb901fd
3
+ size 16654942784
Bagel-Hermes-34B-Slerp-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f140161151549bb35d6fb8560b414c7ff71292e7f7a87ad54b0f2b627b9bf3
3
+ size 14960312896
Bagel-Hermes-34B-Slerp-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf765d7489e335e9748d0afb1fc707d8039ddea47b709c0c580ea7ec7f7bfa4c
3
+ size 19466549664
Bagel-Hermes-34B-Slerp-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c2ea94f8d81b5a4c67b3febfcae7041707243b78be8b48df0ed3f33c546178
3
+ size 20658731424
Bagel-Hermes-34B-Slerp-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1d3e4929ac83ecaf7959f0f06603b54c0792ac0da65b2ac7e48117779c45b4e
3
+ size 19598670240
Bagel-Hermes-34B-Slerp-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b44f13cbab28f9cc2d467eedefb3fde6a939ace71a8d8ba67d04894dc926c244
3
+ size 23707713696
Bagel-Hermes-34B-Slerp-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:068a4e63fec89e6513922b20396966d36e9c0edf984274a70a89cf31efc32cdd
3
+ size 24321867936
Bagel-Hermes-34B-Slerp-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b12c0d8f39f2a6c7bded532d59043a193b72dac020fdb5945a4550c0929df6aa
3
+ size 23707713696
Bagel-Hermes-34B-Slerp-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e5a1d9a5a6145af19d4adcd963c18094b4ab9e9c99e631318042317c12290d5
3
+ size 28213950496
Bagel-Hermes-34B-Slerp-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab091f4ac4ceaeda77b01d2e38982a1c9f95e1a7fefe31c7e7e813cad0778ce0
3
+ size 36542313248
README.md ADDED
@@ -0,0 +1,271 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - mergekit
5
+ - merge
6
+ - TensorBlock
7
+ - GGUF
8
+ base_model: Weyaxi/Bagel-Hermes-34B-Slerp
9
+ model-index:
10
+ - name: Bagel-Hermes-34B-Slerp
11
+ results:
12
+ - task:
13
+ type: text-generation
14
+ name: Text Generation
15
+ dataset:
16
+ name: AI2 Reasoning Challenge (25-Shot)
17
+ type: ai2_arc
18
+ config: ARC-Challenge
19
+ split: test
20
+ args:
21
+ num_few_shot: 25
22
+ metrics:
23
+ - type: acc_norm
24
+ value: 70.73
25
+ name: normalized accuracy
26
+ source:
27
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-34B-Slerp
28
+ name: Open LLM Leaderboard
29
+ - task:
30
+ type: text-generation
31
+ name: Text Generation
32
+ dataset:
33
+ name: HellaSwag (10-Shot)
34
+ type: hellaswag
35
+ split: validation
36
+ args:
37
+ num_few_shot: 10
38
+ metrics:
39
+ - type: acc_norm
40
+ value: 85.68
41
+ name: normalized accuracy
42
+ source:
43
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-34B-Slerp
44
+ name: Open LLM Leaderboard
45
+ - task:
46
+ type: text-generation
47
+ name: Text Generation
48
+ dataset:
49
+ name: MMLU (5-Shot)
50
+ type: cais/mmlu
51
+ config: all
52
+ split: test
53
+ args:
54
+ num_few_shot: 5
55
+ metrics:
56
+ - type: acc
57
+ value: 77.29
58
+ name: accuracy
59
+ source:
60
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-34B-Slerp
61
+ name: Open LLM Leaderboard
62
+ - task:
63
+ type: text-generation
64
+ name: Text Generation
65
+ dataset:
66
+ name: TruthfulQA (0-shot)
67
+ type: truthful_qa
68
+ config: multiple_choice
69
+ split: validation
70
+ args:
71
+ num_few_shot: 0
72
+ metrics:
73
+ - type: mc2
74
+ value: 67.09
75
+ source:
76
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-34B-Slerp
77
+ name: Open LLM Leaderboard
78
+ - task:
79
+ type: text-generation
80
+ name: Text Generation
81
+ dataset:
82
+ name: Winogrande (5-shot)
83
+ type: winogrande
84
+ config: winogrande_xl
85
+ split: validation
86
+ args:
87
+ num_few_shot: 5
88
+ metrics:
89
+ - type: acc
90
+ value: 84.37
91
+ name: accuracy
92
+ source:
93
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-34B-Slerp
94
+ name: Open LLM Leaderboard
95
+ - task:
96
+ type: text-generation
97
+ name: Text Generation
98
+ dataset:
99
+ name: GSM8k (5-shot)
100
+ type: gsm8k
101
+ config: main
102
+ split: test
103
+ args:
104
+ num_few_shot: 5
105
+ metrics:
106
+ - type: acc
107
+ value: 66.26
108
+ name: accuracy
109
+ source:
110
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-34B-Slerp
111
+ name: Open LLM Leaderboard
112
+ - task:
113
+ type: text-generation
114
+ name: Text Generation
115
+ dataset:
116
+ name: IFEval (0-Shot)
117
+ type: HuggingFaceH4/ifeval
118
+ args:
119
+ num_few_shot: 0
120
+ metrics:
121
+ - type: inst_level_strict_acc and prompt_level_strict_acc
122
+ value: 46.03
123
+ name: strict accuracy
124
+ source:
125
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-34B-Slerp
126
+ name: Open LLM Leaderboard
127
+ - task:
128
+ type: text-generation
129
+ name: Text Generation
130
+ dataset:
131
+ name: BBH (3-Shot)
132
+ type: BBH
133
+ args:
134
+ num_few_shot: 3
135
+ metrics:
136
+ - type: acc_norm
137
+ value: 41.96
138
+ name: normalized accuracy
139
+ source:
140
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-34B-Slerp
141
+ name: Open LLM Leaderboard
142
+ - task:
143
+ type: text-generation
144
+ name: Text Generation
145
+ dataset:
146
+ name: MATH Lvl 5 (4-Shot)
147
+ type: hendrycks/competition_math
148
+ args:
149
+ num_few_shot: 4
150
+ metrics:
151
+ - type: exact_match
152
+ value: 4.91
153
+ name: exact match
154
+ source:
155
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-34B-Slerp
156
+ name: Open LLM Leaderboard
157
+ - task:
158
+ type: text-generation
159
+ name: Text Generation
160
+ dataset:
161
+ name: GPQA (0-shot)
162
+ type: Idavidrein/gpqa
163
+ args:
164
+ num_few_shot: 0
165
+ metrics:
166
+ - type: acc_norm
167
+ value: 11.3
168
+ name: acc_norm
169
+ source:
170
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-34B-Slerp
171
+ name: Open LLM Leaderboard
172
+ - task:
173
+ type: text-generation
174
+ name: Text Generation
175
+ dataset:
176
+ name: MuSR (0-shot)
177
+ type: TAUR-Lab/MuSR
178
+ args:
179
+ num_few_shot: 0
180
+ metrics:
181
+ - type: acc_norm
182
+ value: 17.01
183
+ name: acc_norm
184
+ source:
185
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-34B-Slerp
186
+ name: Open LLM Leaderboard
187
+ - task:
188
+ type: text-generation
189
+ name: Text Generation
190
+ dataset:
191
+ name: MMLU-PRO (5-shot)
192
+ type: TIGER-Lab/MMLU-Pro
193
+ config: main
194
+ split: test
195
+ args:
196
+ num_few_shot: 5
197
+ metrics:
198
+ - type: acc
199
+ value: 41.15
200
+ name: accuracy
201
+ source:
202
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Weyaxi/Bagel-Hermes-34B-Slerp
203
+ name: Open LLM Leaderboard
204
+ ---
205
+
206
+ <div style="width: auto; margin-left: auto; margin-right: auto">
207
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
208
+ </div>
209
+ <div style="display: flex; justify-content: space-between; width: 100%;">
210
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
211
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
212
+ 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>
213
+ </p>
214
+ </div>
215
+ </div>
216
+
217
+ ## Weyaxi/Bagel-Hermes-34B-Slerp - GGUF
218
+
219
+ This repo contains GGUF format model files for [Weyaxi/Bagel-Hermes-34B-Slerp](https://huggingface.co/Weyaxi/Bagel-Hermes-34B-Slerp).
220
+
221
+ 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).
222
+
223
+ ## Prompt template
224
+
225
+ ```
226
+ [INST] <<SYS>>
227
+ {system_prompt}
228
+ <</SYS>>
229
+
230
+ {prompt} [/INST]
231
+ ```
232
+
233
+ ## Model file specification
234
+
235
+ | Filename | Quant type | File Size | Description |
236
+ | -------- | ---------- | --------- | ----------- |
237
+ | [Bagel-Hermes-34B-Slerp-Q2_K.gguf](https://huggingface.co/tensorblock/Bagel-Hermes-34B-Slerp-GGUF/tree/main/Bagel-Hermes-34B-Slerp-Q2_K.gguf) | Q2_K | 11.944 GB | smallest, significant quality loss - not recommended for most purposes |
238
+ | [Bagel-Hermes-34B-Slerp-Q3_K_S.gguf](https://huggingface.co/tensorblock/Bagel-Hermes-34B-Slerp-GGUF/tree/main/Bagel-Hermes-34B-Slerp-Q3_K_S.gguf) | Q3_K_S | 13.933 GB | very small, high quality loss |
239
+ | [Bagel-Hermes-34B-Slerp-Q3_K_M.gguf](https://huggingface.co/tensorblock/Bagel-Hermes-34B-Slerp-GGUF/tree/main/Bagel-Hermes-34B-Slerp-Q3_K_M.gguf) | Q3_K_M | 15.511 GB | very small, high quality loss |
240
+ | [Bagel-Hermes-34B-Slerp-Q3_K_L.gguf](https://huggingface.co/tensorblock/Bagel-Hermes-34B-Slerp-GGUF/tree/main/Bagel-Hermes-34B-Slerp-Q3_K_L.gguf) | Q3_K_L | 16.894 GB | small, substantial quality loss |
241
+ | [Bagel-Hermes-34B-Slerp-Q4_0.gguf](https://huggingface.co/tensorblock/Bagel-Hermes-34B-Slerp-GGUF/tree/main/Bagel-Hermes-34B-Slerp-Q4_0.gguf) | Q4_0 | 18.130 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
242
+ | [Bagel-Hermes-34B-Slerp-Q4_K_S.gguf](https://huggingface.co/tensorblock/Bagel-Hermes-34B-Slerp-GGUF/tree/main/Bagel-Hermes-34B-Slerp-Q4_K_S.gguf) | Q4_K_S | 18.253 GB | small, greater quality loss |
243
+ | [Bagel-Hermes-34B-Slerp-Q4_K_M.gguf](https://huggingface.co/tensorblock/Bagel-Hermes-34B-Slerp-GGUF/tree/main/Bagel-Hermes-34B-Slerp-Q4_K_M.gguf) | Q4_K_M | 19.240 GB | medium, balanced quality - recommended |
244
+ | [Bagel-Hermes-34B-Slerp-Q5_0.gguf](https://huggingface.co/tensorblock/Bagel-Hermes-34B-Slerp-GGUF/tree/main/Bagel-Hermes-34B-Slerp-Q5_0.gguf) | Q5_0 | 22.080 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
245
+ | [Bagel-Hermes-34B-Slerp-Q5_K_S.gguf](https://huggingface.co/tensorblock/Bagel-Hermes-34B-Slerp-GGUF/tree/main/Bagel-Hermes-34B-Slerp-Q5_K_S.gguf) | Q5_K_S | 22.080 GB | large, low quality loss - recommended |
246
+ | [Bagel-Hermes-34B-Slerp-Q5_K_M.gguf](https://huggingface.co/tensorblock/Bagel-Hermes-34B-Slerp-GGUF/tree/main/Bagel-Hermes-34B-Slerp-Q5_K_M.gguf) | Q5_K_M | 22.652 GB | large, very low quality loss - recommended |
247
+ | [Bagel-Hermes-34B-Slerp-Q6_K.gguf](https://huggingface.co/tensorblock/Bagel-Hermes-34B-Slerp-GGUF/tree/main/Bagel-Hermes-34B-Slerp-Q6_K.gguf) | Q6_K | 26.276 GB | very large, extremely low quality loss |
248
+ | [Bagel-Hermes-34B-Slerp-Q8_0.gguf](https://huggingface.co/tensorblock/Bagel-Hermes-34B-Slerp-GGUF/tree/main/Bagel-Hermes-34B-Slerp-Q8_0.gguf) | Q8_0 | 34.033 GB | very large, extremely low quality loss - not recommended |
249
+
250
+
251
+ ## Downloading instruction
252
+
253
+ ### Command line
254
+
255
+ Firstly, install Huggingface Client
256
+
257
+ ```shell
258
+ pip install -U "huggingface_hub[cli]"
259
+ ```
260
+
261
+ Then, downoad the individual model file the a local directory
262
+
263
+ ```shell
264
+ huggingface-cli download tensorblock/Bagel-Hermes-34B-Slerp-GGUF --include "Bagel-Hermes-34B-Slerp-Q2_K.gguf" --local-dir MY_LOCAL_DIR
265
+ ```
266
+
267
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
268
+
269
+ ```shell
270
+ huggingface-cli download tensorblock/Bagel-Hermes-34B-Slerp-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
271
+ ```