morriszms commited on
Commit
5326155
1 Parent(s): 4f7c841

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-3-8B-Instruct-DPO-v0.3-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Llama-3-8B-Instruct-DPO-v0.3-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Llama-3-8B-Instruct-DPO-v0.3-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Llama-3-8B-Instruct-DPO-v0.3-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Llama-3-8B-Instruct-DPO-v0.3-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Llama-3-8B-Instruct-DPO-v0.3-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Llama-3-8B-Instruct-DPO-v0.3-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Llama-3-8B-Instruct-DPO-v0.3-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Llama-3-8B-Instruct-DPO-v0.3-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Llama-3-8B-Instruct-DPO-v0.3-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Llama-3-8B-Instruct-DPO-v0.3-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Llama-3-8B-Instruct-DPO-v0.3-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3-8B-Instruct-DPO-v0.3-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3676f1d3935da6ff30344d5db19c711221f3d1f1d65b4e0b2ff1cf45b7053422
3
+ size 3179137024
Llama-3-8B-Instruct-DPO-v0.3-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd6560aae914b46f74621a01fad6236ad1ef638a3757928635fd904b5d3e1ee
3
+ size 4321962400
Llama-3-8B-Instruct-DPO-v0.3-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:041d33c0c1db6b565838a7c2ba4c2fc613feb15236e81d23d5eb8e1315c4d972
3
+ size 4018923936
Llama-3-8B-Instruct-DPO-v0.3-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66cde64dafc491a3d83d8bf5ba4293ba1e6b02c1192f8b06ef313af709ebc5ad
3
+ size 3664505248
Llama-3-8B-Instruct-DPO-v0.3-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db2a4a04072ad664c88fd56473cb2e98fc3a33c319764c7c23a35df7d75fc127
3
+ size 4661218240
Llama-3-8B-Instruct-DPO-v0.3-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b0ebe9421d88ce7b8c7aee04c22260e5c2ddccc1be7776d880295b7cf0b04db
3
+ size 4920740800
Llama-3-8B-Instruct-DPO-v0.3-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cd7113d1e17843b21eb60c836a498302d4eb7cd6ca904887e3992708850324a
3
+ size 4692675520
Llama-3-8B-Instruct-DPO-v0.3-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73c541df533b238e1e3c3956046fb09eae17519858f42bedc4c583efb50b4275
3
+ size 5599301056
Llama-3-8B-Instruct-DPO-v0.3-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c32dbe8b953140a035b394ab6ed3722c4bc981dd13c8f65e173ae61ccd807e0a
3
+ size 5732994496
Llama-3-8B-Instruct-DPO-v0.3-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24460518f831ce90a6d795ab5a49899969def060b22468fb7ecf76af96241a69
3
+ size 5599301056
Llama-3-8B-Instruct-DPO-v0.3-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c301f8763c955f9f95f76978b04225232894c11aec2dea64573faee4405b998
3
+ size 6596014048
Llama-3-8B-Instruct-DPO-v0.3-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a13b6349836fb69b5948078a036a717e4240f5065b275846bc3c2a42c7ca9d3
3
+ size 8540780448
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: llama3
5
+ library_name: transformers
6
+ tags:
7
+ - axolotl
8
+ - finetune
9
+ - dpo
10
+ - facebook
11
+ - meta
12
+ - pytorch
13
+ - llama
14
+ - llama-3
15
+ - TensorBlock
16
+ - GGUF
17
+ base_model: MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3
18
+ datasets:
19
+ - Intel/orca_dpo_pairs
20
+ pipeline_tag: text-generation
21
+ license_name: llama3
22
+ license_link: LICENSE
23
+ inference: false
24
+ model_creator: MaziyarPanahi
25
+ quantized_by: MaziyarPanahi
26
+ model-index:
27
+ - name: Llama-3-8B-Instruct-DPO-v0.3
28
+ results:
29
+ - task:
30
+ type: text-generation
31
+ name: Text Generation
32
+ dataset:
33
+ name: AI2 Reasoning Challenge (25-Shot)
34
+ type: ai2_arc
35
+ config: ARC-Challenge
36
+ split: test
37
+ args:
38
+ num_few_shot: 25
39
+ metrics:
40
+ - type: acc_norm
41
+ value: 62.63
42
+ name: normalized accuracy
43
+ source:
44
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3
45
+ name: Open LLM Leaderboard
46
+ - task:
47
+ type: text-generation
48
+ name: Text Generation
49
+ dataset:
50
+ name: HellaSwag (10-Shot)
51
+ type: hellaswag
52
+ split: validation
53
+ args:
54
+ num_few_shot: 10
55
+ metrics:
56
+ - type: acc_norm
57
+ value: 79.2
58
+ name: normalized accuracy
59
+ source:
60
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3
61
+ name: Open LLM Leaderboard
62
+ - task:
63
+ type: text-generation
64
+ name: Text Generation
65
+ dataset:
66
+ name: MMLU (5-Shot)
67
+ type: cais/mmlu
68
+ config: all
69
+ split: test
70
+ args:
71
+ num_few_shot: 5
72
+ metrics:
73
+ - type: acc
74
+ value: 68.33
75
+ name: accuracy
76
+ source:
77
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3
78
+ name: Open LLM Leaderboard
79
+ - task:
80
+ type: text-generation
81
+ name: Text Generation
82
+ dataset:
83
+ name: TruthfulQA (0-shot)
84
+ type: truthful_qa
85
+ config: multiple_choice
86
+ split: validation
87
+ args:
88
+ num_few_shot: 0
89
+ metrics:
90
+ - type: mc2
91
+ value: 53.29
92
+ source:
93
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3
94
+ name: Open LLM Leaderboard
95
+ - task:
96
+ type: text-generation
97
+ name: Text Generation
98
+ dataset:
99
+ name: Winogrande (5-shot)
100
+ type: winogrande
101
+ config: winogrande_xl
102
+ split: validation
103
+ args:
104
+ num_few_shot: 5
105
+ metrics:
106
+ - type: acc
107
+ value: 75.37
108
+ name: accuracy
109
+ source:
110
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3
111
+ name: Open LLM Leaderboard
112
+ - task:
113
+ type: text-generation
114
+ name: Text Generation
115
+ dataset:
116
+ name: GSM8k (5-shot)
117
+ type: gsm8k
118
+ config: main
119
+ split: test
120
+ args:
121
+ num_few_shot: 5
122
+ metrics:
123
+ - type: acc
124
+ value: 70.58
125
+ name: accuracy
126
+ source:
127
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3
128
+ name: Open LLM Leaderboard
129
+ ---
130
+
131
+ <div style="width: auto; margin-left: auto; margin-right: auto">
132
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
133
+ </div>
134
+ <div style="display: flex; justify-content: space-between; width: 100%;">
135
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
136
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
137
+ 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>
138
+ </p>
139
+ </div>
140
+ </div>
141
+
142
+ ## MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3 - GGUF
143
+
144
+ This repo contains GGUF format model files for [MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3).
145
+
146
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
147
+
148
+ <div style="text-align: left; margin: 20px 0;">
149
+ <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;">
150
+ Run them on the TensorBlock client using your local machine ↗
151
+ </a>
152
+ </div>
153
+
154
+ ## Prompt template
155
+
156
+ ```
157
+ <|im_start|>system
158
+ {system_prompt}<|im_end|>
159
+ <|im_start|>user
160
+ {prompt}<|im_end|>
161
+ <|im_start|>assistant
162
+ ```
163
+
164
+ ## Model file specification
165
+
166
+ | Filename | Quant type | File Size | Description |
167
+ | -------- | ---------- | --------- | ----------- |
168
+ | [Llama-3-8B-Instruct-DPO-v0.3-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF/blob/main/Llama-3-8B-Instruct-DPO-v0.3-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
169
+ | [Llama-3-8B-Instruct-DPO-v0.3-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF/blob/main/Llama-3-8B-Instruct-DPO-v0.3-Q3_K_S.gguf) | Q3_K_S | 3.665 GB | very small, high quality loss |
170
+ | [Llama-3-8B-Instruct-DPO-v0.3-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF/blob/main/Llama-3-8B-Instruct-DPO-v0.3-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
171
+ | [Llama-3-8B-Instruct-DPO-v0.3-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF/blob/main/Llama-3-8B-Instruct-DPO-v0.3-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
172
+ | [Llama-3-8B-Instruct-DPO-v0.3-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF/blob/main/Llama-3-8B-Instruct-DPO-v0.3-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
173
+ | [Llama-3-8B-Instruct-DPO-v0.3-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF/blob/main/Llama-3-8B-Instruct-DPO-v0.3-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss |
174
+ | [Llama-3-8B-Instruct-DPO-v0.3-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF/blob/main/Llama-3-8B-Instruct-DPO-v0.3-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |
175
+ | [Llama-3-8B-Instruct-DPO-v0.3-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF/blob/main/Llama-3-8B-Instruct-DPO-v0.3-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
176
+ | [Llama-3-8B-Instruct-DPO-v0.3-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF/blob/main/Llama-3-8B-Instruct-DPO-v0.3-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended |
177
+ | [Llama-3-8B-Instruct-DPO-v0.3-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF/blob/main/Llama-3-8B-Instruct-DPO-v0.3-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |
178
+ | [Llama-3-8B-Instruct-DPO-v0.3-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF/blob/main/Llama-3-8B-Instruct-DPO-v0.3-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss |
179
+ | [Llama-3-8B-Instruct-DPO-v0.3-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF/blob/main/Llama-3-8B-Instruct-DPO-v0.3-Q8_0.gguf) | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended |
180
+
181
+
182
+ ## Downloading instruction
183
+
184
+ ### Command line
185
+
186
+ Firstly, install Huggingface Client
187
+
188
+ ```shell
189
+ pip install -U "huggingface_hub[cli]"
190
+ ```
191
+
192
+ Then, downoad the individual model file the a local directory
193
+
194
+ ```shell
195
+ huggingface-cli download tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF --include "Llama-3-8B-Instruct-DPO-v0.3-Q2_K.gguf" --local-dir MY_LOCAL_DIR
196
+ ```
197
+
198
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
199
+
200
+ ```shell
201
+ huggingface-cli download tensorblock/Llama-3-8B-Instruct-DPO-v0.3-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
202
+ ```