morriszms commited on
Commit
2cbf4fb
·
verified ·
1 Parent(s): 11934ad

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
+ FluentlyLM-Prinum-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ FluentlyLM-Prinum-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ FluentlyLM-Prinum-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ FluentlyLM-Prinum-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ FluentlyLM-Prinum-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ FluentlyLM-Prinum-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ FluentlyLM-Prinum-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ FluentlyLM-Prinum-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ FluentlyLM-Prinum-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ FluentlyLM-Prinum-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ FluentlyLM-Prinum-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ FluentlyLM-Prinum-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
FluentlyLM-Prinum-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85fa3a41086e3eb8d72716604ce203545f5a2bc5a05823ec5b1c357520dfc109
3
+ size 12313099584
FluentlyLM-Prinum-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6572a2b289ded31c696fd23a9f3ec18b33af993efebb7092b7cf7eb94a7f4de1
3
+ size 17247079744
FluentlyLM-Prinum-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73ca4420fc0e2a64bf4ed3dae7b18fad515f6cfa1c8c4377eab7445bd55c717
3
+ size 15935049024
FluentlyLM-Prinum-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b1d818f1b09442c4bc25e0d0ba1f432fd27187ed2af80e1f4991d4509b8052d
3
+ size 14392331584
FluentlyLM-Prinum-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d10ded8f6ff774e85cfb5ae4224e82f6fdae477ae827fce6657169817a9e625c
3
+ size 18640231744
FluentlyLM-Prinum-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d79317073caccbab1e13203494b007f83f9b0282b9fa25ca0eef05c118ef356f
3
+ size 19851337024
FluentlyLM-Prinum-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:407dc72645189d3779fdb6cba36e7a9ca35790a78c02c77e142c09ab8dee70a4
3
+ size 18784410944
FluentlyLM-Prinum-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51833616d5b2843bde5b2fda6eb4739e5a71b6b746b065fbbc2b1ff92c6cd510
3
+ size 22638255424
FluentlyLM-Prinum-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e775618df29e474685ddaa20f9b01a46bf78d54e61ce753118031955478202f
3
+ size 23262158144
FluentlyLM-Prinum-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d35a902ecf5ac18a3941115e8bd6a6bb9f64b3b07b6c1fd103d4931c867f1bb
3
+ size 22638255424
FluentlyLM-Prinum-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33ecfc2810967e79ae3dfcd21f4570a47019f63d112d293a3d6cee520358fe36
3
+ size 26886155584
FluentlyLM-Prinum-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b58a430ac28f3199553d0d1ee3bd604d17f3d8f0c9a5f2eb22c10fb16e38122
3
+ size 34820885824
README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - fr
5
+ - es
6
+ - ru
7
+ - zh
8
+ - ja
9
+ - fa
10
+ - code
11
+ license: mit
12
+ library_name: transformers
13
+ tags:
14
+ - fluently-lm
15
+ - fluently
16
+ - prinum
17
+ - instruct
18
+ - trained
19
+ - math
20
+ - roleplay
21
+ - reasoning
22
+ - axolotl
23
+ - unsloth
24
+ - argilla
25
+ - qwen2
26
+ - TensorBlock
27
+ - GGUF
28
+ datasets:
29
+ - fluently-sets/ultraset
30
+ - fluently-sets/ultrathink
31
+ - fluently-sets/reasoning-1-1k
32
+ - fluently-sets/MATH-500-Overall
33
+ inference: true
34
+ pipeline_tag: text-generation
35
+ base_model: fluently-lm/FluentlyLM-Prinum
36
+ model-index:
37
+ - name: FluentlyLM-Prinum
38
+ results:
39
+ - task:
40
+ type: text-generation
41
+ name: Text Generation
42
+ dataset:
43
+ name: IFEval (0-Shot)
44
+ type: HuggingFaceH4/ifeval
45
+ args:
46
+ num_few_shot: 0
47
+ metrics:
48
+ - type: inst_level_strict_acc and prompt_level_strict_acc
49
+ value: 80.9
50
+ name: strict accuracy
51
+ source:
52
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
53
+ name: Open LLM Leaderboard
54
+ - task:
55
+ type: text-generation
56
+ name: Text Generation
57
+ dataset:
58
+ name: BBH (3-Shot)
59
+ type: BBH
60
+ args:
61
+ num_few_shot: 3
62
+ metrics:
63
+ - type: acc_norm
64
+ value: 59.48
65
+ name: normalized accuracy
66
+ source:
67
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
68
+ name: Open LLM Leaderboard
69
+ - task:
70
+ type: text-generation
71
+ name: Text Generation
72
+ dataset:
73
+ name: MATH Lvl 5 (4-Shot)
74
+ type: hendrycks/competition_math
75
+ args:
76
+ num_few_shot: 4
77
+ metrics:
78
+ - type: exact_match
79
+ value: 54.0
80
+ name: exact match
81
+ source:
82
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
83
+ name: Open LLM Leaderboard
84
+ - task:
85
+ type: text-generation
86
+ name: Text Generation
87
+ dataset:
88
+ name: GPQA (0-shot)
89
+ type: Idavidrein/gpqa
90
+ args:
91
+ num_few_shot: 0
92
+ metrics:
93
+ - type: acc_norm
94
+ value: 18.23
95
+ name: acc_norm
96
+ source:
97
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
98
+ name: Open LLM Leaderboard
99
+ - task:
100
+ type: text-generation
101
+ name: Text Generation
102
+ dataset:
103
+ name: MuSR (0-shot)
104
+ type: TAUR-Lab/MuSR
105
+ args:
106
+ num_few_shot: 0
107
+ metrics:
108
+ - type: acc_norm
109
+ value: 17.26
110
+ name: acc_norm
111
+ source:
112
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
113
+ name: Open LLM Leaderboard
114
+ - task:
115
+ type: text-generation
116
+ name: Text Generation
117
+ dataset:
118
+ name: MMLU-PRO (5-shot)
119
+ type: TIGER-Lab/MMLU-Pro
120
+ config: main
121
+ split: test
122
+ args:
123
+ num_few_shot: 5
124
+ metrics:
125
+ - type: acc
126
+ value: 53.42
127
+ name: accuracy
128
+ source:
129
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=fluently-lm/FluentlyLM-Prinum
130
+ name: Open LLM Leaderboard
131
+ ---
132
+
133
+ <div style="width: auto; margin-left: auto; margin-right: auto">
134
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
135
+ </div>
136
+ <div style="display: flex; justify-content: space-between; width: 100%;">
137
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
138
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
139
+ 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>
140
+ </p>
141
+ </div>
142
+ </div>
143
+
144
+ ## fluently-lm/FluentlyLM-Prinum - GGUF
145
+
146
+ This repo contains GGUF format model files for [fluently-lm/FluentlyLM-Prinum](https://huggingface.co/fluently-lm/FluentlyLM-Prinum).
147
+
148
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4823](https://github.com/ggml-org/llama.cpp/commit/5bbe6a9fe9a8796a9389c85accec89dbc4d91e39).
149
+
150
+ <div style="text-align: left; margin: 20px 0;">
151
+ <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
152
+ Run them on the TensorBlock client using your local machine ↗
153
+ </a>
154
+ </div>
155
+
156
+ ## Prompt template
157
+
158
+ ```
159
+ <|im_start|>system
160
+ {system_prompt}<|im_end|>
161
+ <|im_start|>user
162
+ {prompt}<|im_end|>
163
+ <|im_start|>assistant
164
+ ```
165
+
166
+ ## Model file specification
167
+
168
+ | Filename | Quant type | File Size | Description |
169
+ | -------- | ---------- | --------- | ----------- |
170
+ | [FluentlyLM-Prinum-Q2_K.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q2_K.gguf) | Q2_K | 12.313 GB | smallest, significant quality loss - not recommended for most purposes |
171
+ | [FluentlyLM-Prinum-Q3_K_S.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q3_K_S.gguf) | Q3_K_S | 14.392 GB | very small, high quality loss |
172
+ | [FluentlyLM-Prinum-Q3_K_M.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q3_K_M.gguf) | Q3_K_M | 15.935 GB | very small, high quality loss |
173
+ | [FluentlyLM-Prinum-Q3_K_L.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q3_K_L.gguf) | Q3_K_L | 17.247 GB | small, substantial quality loss |
174
+ | [FluentlyLM-Prinum-Q4_0.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q4_0.gguf) | Q4_0 | 18.640 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
175
+ | [FluentlyLM-Prinum-Q4_K_S.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q4_K_S.gguf) | Q4_K_S | 18.784 GB | small, greater quality loss |
176
+ | [FluentlyLM-Prinum-Q4_K_M.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q4_K_M.gguf) | Q4_K_M | 19.851 GB | medium, balanced quality - recommended |
177
+ | [FluentlyLM-Prinum-Q5_0.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q5_0.gguf) | Q5_0 | 22.638 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
178
+ | [FluentlyLM-Prinum-Q5_K_S.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q5_K_S.gguf) | Q5_K_S | 22.638 GB | large, low quality loss - recommended |
179
+ | [FluentlyLM-Prinum-Q5_K_M.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q5_K_M.gguf) | Q5_K_M | 23.262 GB | large, very low quality loss - recommended |
180
+ | [FluentlyLM-Prinum-Q6_K.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q6_K.gguf) | Q6_K | 26.886 GB | very large, extremely low quality loss |
181
+ | [FluentlyLM-Prinum-Q8_0.gguf](https://huggingface.co/tensorblock/FluentlyLM-Prinum-GGUF/blob/main/FluentlyLM-Prinum-Q8_0.gguf) | Q8_0 | 34.821 GB | very large, extremely low quality loss - not recommended |
182
+
183
+
184
+ ## Downloading instruction
185
+
186
+ ### Command line
187
+
188
+ Firstly, install Huggingface Client
189
+
190
+ ```shell
191
+ pip install -U "huggingface_hub[cli]"
192
+ ```
193
+
194
+ Then, downoad the individual model file the a local directory
195
+
196
+ ```shell
197
+ huggingface-cli download tensorblock/FluentlyLM-Prinum-GGUF --include "FluentlyLM-Prinum-Q2_K.gguf" --local-dir MY_LOCAL_DIR
198
+ ```
199
+
200
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
201
+
202
+ ```shell
203
+ huggingface-cli download tensorblock/FluentlyLM-Prinum-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
204
+ ```