morriszms commited on
Commit
70375b5
1 Parent(s): efcfd7e

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
+ Llama-3.1-8B-MultiReflection-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Llama-3.1-8B-MultiReflection-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Llama-3.1-8B-MultiReflection-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Llama-3.1-8B-MultiReflection-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Llama-3.1-8B-MultiReflection-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Llama-3.1-8B-MultiReflection-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Llama-3.1-8B-MultiReflection-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Llama-3.1-8B-MultiReflection-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Llama-3.1-8B-MultiReflection-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Llama-3.1-8B-MultiReflection-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Llama-3.1-8B-MultiReflection-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Llama-3.1-8B-MultiReflection-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-MultiReflection-Instruct-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93b74b06d85e868e48778532dcd1ff0114f11554a8c3a109856d83ad1fcb2713
3
+ size 3179136608
Llama-3.1-8B-MultiReflection-Instruct-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d632bdc5e9c6b5ed24ca5d759a05607bf47e1a7f8191f566e6b6453be0236c1
3
+ size 4321961568
Llama-3.1-8B-MultiReflection-Instruct-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb0fd0da8e528af24096c2aad156076d80eef225bceedebd29474e70b60cabd
3
+ size 4018923104
Llama-3.1-8B-MultiReflection-Instruct-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd295f9c778a7853bfc0590f0c152d084ad98f6f9916814d712ff45025588c6b
3
+ size 3664504416
Llama-3.1-8B-MultiReflection-Instruct-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7522e30dd0f7a2103c17af5a73f6f9c0d2c9f520643cb6c72e01d477bb8d1de
3
+ size 4661216864
Llama-3.1-8B-MultiReflection-Instruct-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1e1edb42f6f8dbbe95dfc4634d62aae0a28b6086ee3007f61a8945a8adb12da
3
+ size 4920739424
Llama-3.1-8B-MultiReflection-Instruct-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efd7f92e5618abf3d93437ef86e054a0f74dd0784e69e62d46446c580f224058
3
+ size 4692674144
Llama-3.1-8B-MultiReflection-Instruct-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:324b4b8f9a8ef04b93c41c89d57d647631c4e147d1fddd6b94ec3e73f4f2d0bb
3
+ size 5599299168
Llama-3.1-8B-MultiReflection-Instruct-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45f000a9c0ff6a24266f3cb43ed196482880aefd5c3fd607163a78637c47a377
3
+ size 5732992608
Llama-3.1-8B-MultiReflection-Instruct-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37100721973e56df4c21c195c6e9fa82636065147d13177db170b051182b56e1
3
+ size 5599299168
Llama-3.1-8B-MultiReflection-Instruct-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703bcd2b27f996c14b5c36a0e421773e3f0d5fc6cbc1dc2ba75a7e44d49dda33
3
+ size 6596011616
Llama-3.1-8B-MultiReflection-Instruct-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0112090d6837dabd3017e6e2d9d74ff0940d7e00a2900249e24453bd891e1d74
3
+ size 8540776032
README.md ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - de
5
+ - fr
6
+ - it
7
+ - pt
8
+ - hi
9
+ - es
10
+ - th
11
+ license: llama3.1
12
+ library_name: transformers
13
+ tags:
14
+ - reflection
15
+ - unsloth
16
+ - peft
17
+ - llama
18
+ - TensorBlock
19
+ - GGUF
20
+ base_model: leafspark/Llama-3.1-8B-MultiReflection-Instruct
21
+ datasets:
22
+ - leafspark/DetailedReflection-Claude-v3_5-Sonnet
23
+ metrics:
24
+ - accuracy
25
+ pipeline_tag: text-generation
26
+ model-index:
27
+ - name: Llama-3.1-8B-MultiReflection-Instruct
28
+ results:
29
+ - task:
30
+ type: text-generation
31
+ name: Text Generation
32
+ dataset:
33
+ name: IFEval (0-Shot)
34
+ type: HuggingFaceH4/ifeval
35
+ args:
36
+ num_few_shot: 0
37
+ metrics:
38
+ - type: inst_level_strict_acc and prompt_level_strict_acc
39
+ value: 71.25
40
+ name: strict accuracy
41
+ source:
42
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
43
+ name: Open LLM Leaderboard
44
+ - task:
45
+ type: text-generation
46
+ name: Text Generation
47
+ dataset:
48
+ name: BBH (3-Shot)
49
+ type: BBH
50
+ args:
51
+ num_few_shot: 3
52
+ metrics:
53
+ - type: acc_norm
54
+ value: 28.45
55
+ name: normalized accuracy
56
+ source:
57
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
58
+ name: Open LLM Leaderboard
59
+ - task:
60
+ type: text-generation
61
+ name: Text Generation
62
+ dataset:
63
+ name: MATH Lvl 5 (4-Shot)
64
+ type: hendrycks/competition_math
65
+ args:
66
+ num_few_shot: 4
67
+ metrics:
68
+ - type: exact_match
69
+ value: 12.54
70
+ name: exact match
71
+ source:
72
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
73
+ name: Open LLM Leaderboard
74
+ - task:
75
+ type: text-generation
76
+ name: Text Generation
77
+ dataset:
78
+ name: GPQA (0-shot)
79
+ type: Idavidrein/gpqa
80
+ args:
81
+ num_few_shot: 0
82
+ metrics:
83
+ - type: acc_norm
84
+ value: 5.7
85
+ name: acc_norm
86
+ source:
87
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
88
+ name: Open LLM Leaderboard
89
+ - task:
90
+ type: text-generation
91
+ name: Text Generation
92
+ dataset:
93
+ name: MuSR (0-shot)
94
+ type: TAUR-Lab/MuSR
95
+ args:
96
+ num_few_shot: 0
97
+ metrics:
98
+ - type: acc_norm
99
+ value: 8.52
100
+ name: acc_norm
101
+ source:
102
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
103
+ name: Open LLM Leaderboard
104
+ - task:
105
+ type: text-generation
106
+ name: Text Generation
107
+ dataset:
108
+ name: MMLU-PRO (5-shot)
109
+ type: TIGER-Lab/MMLU-Pro
110
+ config: main
111
+ split: test
112
+ args:
113
+ num_few_shot: 5
114
+ metrics:
115
+ - type: acc
116
+ value: 30.27
117
+ name: accuracy
118
+ source:
119
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
120
+ name: Open LLM Leaderboard
121
+ ---
122
+
123
+ <div style="width: auto; margin-left: auto; margin-right: auto">
124
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
125
+ </div>
126
+ <div style="display: flex; justify-content: space-between; width: 100%;">
127
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
128
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
129
+ 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>
130
+ </p>
131
+ </div>
132
+ </div>
133
+
134
+ ## leafspark/Llama-3.1-8B-MultiReflection-Instruct - GGUF
135
+
136
+ This repo contains GGUF format model files for [leafspark/Llama-3.1-8B-MultiReflection-Instruct](https://huggingface.co/leafspark/Llama-3.1-8B-MultiReflection-Instruct).
137
+
138
+ 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).
139
+
140
+ ## Prompt template
141
+
142
+ ```
143
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
144
+
145
+ Cutting Knowledge Date: December 2023
146
+ Today Date: 26 Jul 2024
147
+
148
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
149
+
150
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
151
+ ```
152
+
153
+ ## Model file specification
154
+
155
+ | Filename | Quant type | File Size | Description |
156
+ | -------- | ---------- | --------- | ----------- |
157
+ | [Llama-3.1-8B-MultiReflection-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF/tree/main/Llama-3.1-8B-MultiReflection-Instruct-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
158
+ | [Llama-3.1-8B-MultiReflection-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF/tree/main/Llama-3.1-8B-MultiReflection-Instruct-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
159
+ | [Llama-3.1-8B-MultiReflection-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF/tree/main/Llama-3.1-8B-MultiReflection-Instruct-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
160
+ | [Llama-3.1-8B-MultiReflection-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF/tree/main/Llama-3.1-8B-MultiReflection-Instruct-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
161
+ | [Llama-3.1-8B-MultiReflection-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF/tree/main/Llama-3.1-8B-MultiReflection-Instruct-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
162
+ | [Llama-3.1-8B-MultiReflection-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF/tree/main/Llama-3.1-8B-MultiReflection-Instruct-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
163
+ | [Llama-3.1-8B-MultiReflection-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF/tree/main/Llama-3.1-8B-MultiReflection-Instruct-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
164
+ | [Llama-3.1-8B-MultiReflection-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF/tree/main/Llama-3.1-8B-MultiReflection-Instruct-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
165
+ | [Llama-3.1-8B-MultiReflection-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF/tree/main/Llama-3.1-8B-MultiReflection-Instruct-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
166
+ | [Llama-3.1-8B-MultiReflection-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF/tree/main/Llama-3.1-8B-MultiReflection-Instruct-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
167
+ | [Llama-3.1-8B-MultiReflection-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF/tree/main/Llama-3.1-8B-MultiReflection-Instruct-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
168
+ | [Llama-3.1-8B-MultiReflection-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF/tree/main/Llama-3.1-8B-MultiReflection-Instruct-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
169
+
170
+
171
+ ## Downloading instruction
172
+
173
+ ### Command line
174
+
175
+ Firstly, install Huggingface Client
176
+
177
+ ```shell
178
+ pip install -U "huggingface_hub[cli]"
179
+ ```
180
+
181
+ Then, downoad the individual model file the a local directory
182
+
183
+ ```shell
184
+ huggingface-cli download tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF --include "Llama-3.1-8B-MultiReflection-Instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
185
+ ```
186
+
187
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
188
+
189
+ ```shell
190
+ huggingface-cli download tensorblock/Llama-3.1-8B-MultiReflection-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
191
+ ```