morriszms commited on
Commit
15b1697
·
verified ·
1 Parent(s): 9c6ceb1

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
+ MiaLatte-Indo-Mistral-7b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ MiaLatte-Indo-Mistral-7b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ MiaLatte-Indo-Mistral-7b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ MiaLatte-Indo-Mistral-7b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ MiaLatte-Indo-Mistral-7b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ MiaLatte-Indo-Mistral-7b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ MiaLatte-Indo-Mistral-7b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ MiaLatte-Indo-Mistral-7b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ MiaLatte-Indo-Mistral-7b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ MiaLatte-Indo-Mistral-7b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ MiaLatte-Indo-Mistral-7b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ MiaLatte-Indo-Mistral-7b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
MiaLatte-Indo-Mistral-7b-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab6672a6d210f4dffd95fbeb19d42f994eb2d19bd601936f05093cbca42f952
3
+ size 2719242912
MiaLatte-Indo-Mistral-7b-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40d186437a1bf7f9f594131865f3f7150c260f255d2cfcbede7db5ebdfed4fb
3
+ size 3822025376
MiaLatte-Indo-Mistral-7b-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:966c1b8db75c93f074a61812ea2dea4609d8e8059a6d6de9fb67a200f780b607
3
+ size 3518986912
MiaLatte-Indo-Mistral-7b-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbe7c3988048fa7bdcedf06e40d8388eade94b3b0854a4f837b0a1db8e555b2f
3
+ size 3164568224
MiaLatte-Indo-Mistral-7b-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1977d2d00ba8161f54ba9b93ec662f57e15135ab4d726804f10e2933587d54f1
3
+ size 4108917408
MiaLatte-Indo-Mistral-7b-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a92fa360f2b36f2f329a3f11deb9c53a9eec8e685b4e57964a80e311a7dcabf
3
+ size 4368439968
MiaLatte-Indo-Mistral-7b-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5dcfc7b5cf06bd2fd76e4afad60094dc27ca55168ab4eb4b02de58c5519fc9
3
+ size 4140374688
MiaLatte-Indo-Mistral-7b-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa4657cafee266c21ae317394756e4b75a02e0369723caf39cbb3dd15f04052e
3
+ size 4997716640
MiaLatte-Indo-Mistral-7b-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9694ab58d09e9764a58fe33c7fd7913bf8fd1089871f7e4f3bf87c20a8a523
3
+ size 5131410080
MiaLatte-Indo-Mistral-7b-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:419f064c48bf3a8936cc612b383fcc20378c17c61dc1bfbbbfc7df1a1cd06a96
3
+ size 4997716640
MiaLatte-Indo-Mistral-7b-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:018d060442f29d37b70f431663a27238202e24c040bc825841c4910c885c6db8
3
+ size 5942065824
MiaLatte-Indo-Mistral-7b-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e728d7f534a8ce86e7bf7b690a5114375258cbbb13ca8125c8a7afdd53c22bb2
3
+ size 7695858336
README.md ADDED
@@ -0,0 +1,184 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - id
4
+ - en
5
+ license: cc-by-nc-4.0
6
+ tags:
7
+ - merge
8
+ - mergekit
9
+ - TensorBlock
10
+ - GGUF
11
+ base_model: indischepartij/MiaLatte-Indo-Mistral-7b
12
+ model-index:
13
+ - name: MiaLatte-Indo-Mistral-7b
14
+ results:
15
+ - task:
16
+ type: text-generation
17
+ name: Text Generation
18
+ dataset:
19
+ name: AI2 Reasoning Challenge (25-Shot)
20
+ type: ai2_arc
21
+ config: ARC-Challenge
22
+ split: test
23
+ args:
24
+ num_few_shot: 25
25
+ metrics:
26
+ - type: acc_norm
27
+ value: 66.55
28
+ name: normalized accuracy
29
+ source:
30
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/MiaLatte-Indo-Mistral-7b
31
+ name: Open LLM Leaderboard
32
+ - task:
33
+ type: text-generation
34
+ name: Text Generation
35
+ dataset:
36
+ name: HellaSwag (10-Shot)
37
+ type: hellaswag
38
+ split: validation
39
+ args:
40
+ num_few_shot: 10
41
+ metrics:
42
+ - type: acc_norm
43
+ value: 85.23
44
+ name: normalized accuracy
45
+ source:
46
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/MiaLatte-Indo-Mistral-7b
47
+ name: Open LLM Leaderboard
48
+ - task:
49
+ type: text-generation
50
+ name: Text Generation
51
+ dataset:
52
+ name: MMLU (5-Shot)
53
+ type: cais/mmlu
54
+ config: all
55
+ split: test
56
+ args:
57
+ num_few_shot: 5
58
+ metrics:
59
+ - type: acc
60
+ value: 63.93
61
+ name: accuracy
62
+ source:
63
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/MiaLatte-Indo-Mistral-7b
64
+ name: Open LLM Leaderboard
65
+ - task:
66
+ type: text-generation
67
+ name: Text Generation
68
+ dataset:
69
+ name: TruthfulQA (0-shot)
70
+ type: truthful_qa
71
+ config: multiple_choice
72
+ split: validation
73
+ args:
74
+ num_few_shot: 0
75
+ metrics:
76
+ - type: mc2
77
+ value: 56.04
78
+ source:
79
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/MiaLatte-Indo-Mistral-7b
80
+ name: Open LLM Leaderboard
81
+ - task:
82
+ type: text-generation
83
+ name: Text Generation
84
+ dataset:
85
+ name: Winogrande (5-shot)
86
+ type: winogrande
87
+ config: winogrande_xl
88
+ split: validation
89
+ args:
90
+ num_few_shot: 5
91
+ metrics:
92
+ - type: acc
93
+ value: 80.35
94
+ name: accuracy
95
+ source:
96
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/MiaLatte-Indo-Mistral-7b
97
+ name: Open LLM Leaderboard
98
+ - task:
99
+ type: text-generation
100
+ name: Text Generation
101
+ dataset:
102
+ name: GSM8k (5-shot)
103
+ type: gsm8k
104
+ config: main
105
+ split: test
106
+ args:
107
+ num_few_shot: 5
108
+ metrics:
109
+ - type: acc
110
+ value: 55.04
111
+ name: accuracy
112
+ source:
113
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/MiaLatte-Indo-Mistral-7b
114
+ name: Open LLM Leaderboard
115
+ ---
116
+
117
+ <div style="width: auto; margin-left: auto; margin-right: auto">
118
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
119
+ </div>
120
+ <div style="display: flex; justify-content: space-between; width: 100%;">
121
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
122
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
123
+ 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>
124
+ </p>
125
+ </div>
126
+ </div>
127
+
128
+ ## indischepartij/MiaLatte-Indo-Mistral-7b - GGUF
129
+
130
+ This repo contains GGUF format model files for [indischepartij/MiaLatte-Indo-Mistral-7b](https://huggingface.co/indischepartij/MiaLatte-Indo-Mistral-7b).
131
+
132
+ 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).
133
+
134
+ <div style="text-align: left; margin: 20px 0;">
135
+ <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;">
136
+ Run them on the TensorBlock client using your local machine ↗
137
+ </a>
138
+ </div>
139
+
140
+ ## Prompt template
141
+
142
+ ```
143
+ <s>[INST] {prompt} [/INST]
144
+ ```
145
+
146
+ ## Model file specification
147
+
148
+ | Filename | Quant type | File Size | Description |
149
+ | -------- | ---------- | --------- | ----------- |
150
+ | [MiaLatte-Indo-Mistral-7b-Q2_K.gguf](https://huggingface.co/tensorblock/MiaLatte-Indo-Mistral-7b-GGUF/blob/main/MiaLatte-Indo-Mistral-7b-Q2_K.gguf) | Q2_K | 2.719 GB | smallest, significant quality loss - not recommended for most purposes |
151
+ | [MiaLatte-Indo-Mistral-7b-Q3_K_S.gguf](https://huggingface.co/tensorblock/MiaLatte-Indo-Mistral-7b-GGUF/blob/main/MiaLatte-Indo-Mistral-7b-Q3_K_S.gguf) | Q3_K_S | 3.165 GB | very small, high quality loss |
152
+ | [MiaLatte-Indo-Mistral-7b-Q3_K_M.gguf](https://huggingface.co/tensorblock/MiaLatte-Indo-Mistral-7b-GGUF/blob/main/MiaLatte-Indo-Mistral-7b-Q3_K_M.gguf) | Q3_K_M | 3.519 GB | very small, high quality loss |
153
+ | [MiaLatte-Indo-Mistral-7b-Q3_K_L.gguf](https://huggingface.co/tensorblock/MiaLatte-Indo-Mistral-7b-GGUF/blob/main/MiaLatte-Indo-Mistral-7b-Q3_K_L.gguf) | Q3_K_L | 3.822 GB | small, substantial quality loss |
154
+ | [MiaLatte-Indo-Mistral-7b-Q4_0.gguf](https://huggingface.co/tensorblock/MiaLatte-Indo-Mistral-7b-GGUF/blob/main/MiaLatte-Indo-Mistral-7b-Q4_0.gguf) | Q4_0 | 4.109 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
155
+ | [MiaLatte-Indo-Mistral-7b-Q4_K_S.gguf](https://huggingface.co/tensorblock/MiaLatte-Indo-Mistral-7b-GGUF/blob/main/MiaLatte-Indo-Mistral-7b-Q4_K_S.gguf) | Q4_K_S | 4.140 GB | small, greater quality loss |
156
+ | [MiaLatte-Indo-Mistral-7b-Q4_K_M.gguf](https://huggingface.co/tensorblock/MiaLatte-Indo-Mistral-7b-GGUF/blob/main/MiaLatte-Indo-Mistral-7b-Q4_K_M.gguf) | Q4_K_M | 4.368 GB | medium, balanced quality - recommended |
157
+ | [MiaLatte-Indo-Mistral-7b-Q5_0.gguf](https://huggingface.co/tensorblock/MiaLatte-Indo-Mistral-7b-GGUF/blob/main/MiaLatte-Indo-Mistral-7b-Q5_0.gguf) | Q5_0 | 4.998 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
158
+ | [MiaLatte-Indo-Mistral-7b-Q5_K_S.gguf](https://huggingface.co/tensorblock/MiaLatte-Indo-Mistral-7b-GGUF/blob/main/MiaLatte-Indo-Mistral-7b-Q5_K_S.gguf) | Q5_K_S | 4.998 GB | large, low quality loss - recommended |
159
+ | [MiaLatte-Indo-Mistral-7b-Q5_K_M.gguf](https://huggingface.co/tensorblock/MiaLatte-Indo-Mistral-7b-GGUF/blob/main/MiaLatte-Indo-Mistral-7b-Q5_K_M.gguf) | Q5_K_M | 5.131 GB | large, very low quality loss - recommended |
160
+ | [MiaLatte-Indo-Mistral-7b-Q6_K.gguf](https://huggingface.co/tensorblock/MiaLatte-Indo-Mistral-7b-GGUF/blob/main/MiaLatte-Indo-Mistral-7b-Q6_K.gguf) | Q6_K | 5.942 GB | very large, extremely low quality loss |
161
+ | [MiaLatte-Indo-Mistral-7b-Q8_0.gguf](https://huggingface.co/tensorblock/MiaLatte-Indo-Mistral-7b-GGUF/blob/main/MiaLatte-Indo-Mistral-7b-Q8_0.gguf) | Q8_0 | 7.696 GB | very large, extremely low quality loss - not recommended |
162
+
163
+
164
+ ## Downloading instruction
165
+
166
+ ### Command line
167
+
168
+ Firstly, install Huggingface Client
169
+
170
+ ```shell
171
+ pip install -U "huggingface_hub[cli]"
172
+ ```
173
+
174
+ Then, downoad the individual model file the a local directory
175
+
176
+ ```shell
177
+ huggingface-cli download tensorblock/MiaLatte-Indo-Mistral-7b-GGUF --include "MiaLatte-Indo-Mistral-7b-Q2_K.gguf" --local-dir MY_LOCAL_DIR
178
+ ```
179
+
180
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
181
+
182
+ ```shell
183
+ huggingface-cli download tensorblock/MiaLatte-Indo-Mistral-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
184
+ ```