Text Generation
GGUF
English
TensorBlock
GGUF
Eval Results
Inference Endpoints
morriszms commited on
Commit
fd22d0a
1 Parent(s): 4e6dc82

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
+ Marx-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Marx-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Marx-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Marx-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Marx-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Marx-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Marx-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Marx-3B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Marx-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Marx-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Marx-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Marx-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Marx-3B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f7a468c577b49bd292fb3ce0874993228e55441ebf8640c883861d85b8e98e
3
+ size 1979924704
Marx-3B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f78c5bb1c36c74dad45429b5d7a9eb199ee56a1c071dbb394f1714a3df4ea43e
3
+ size 2214548704
Marx-3B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029942dc650266fcf558cb1cc62ee7049b52d67c698a654ae1400ab7c3d4b32c
3
+ size 2139348704
Marx-3B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e81f9a3ad30e729436b253d684847b1d22c85559ce9be35913d48ba33a7017c1
3
+ size 1979924704
Marx-3B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c4ceee42b0b641a811a4b8d81f46aebfb188168835cffd9bc47b2f0f26c2202
3
+ size 1979924704
Marx-3B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d55458fcc9802251acd2f0dd108fd96a2a4ac14336331a35ad3d90d1dd62f70
3
+ size 2580116704
Marx-3B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5141db7996560c04b6f889939eb19ea69ed8ec8f4e50fa1c47956271eef1a1be
3
+ size 2403156704
Marx-3B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:435efbd8a81cfb048ab1770ca525bb37b8ececdd73219cc9da3e5aac489603b5
3
+ size 2395412704
Marx-3B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45455903768b8a2adb0d88b6b2751af0bfb6cfaf8fcef2d01705290d4f627d88
3
+ size 2757076704
Marx-3B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56ca42f41bb362c38c7399ebd0f286e855a8a762cf943c57997411c5d7709500
3
+ size 2603156704
Marx-3B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81c871c06042c2a99cc171328fe61914c4089040a89bfe97d4db809733a623a2
3
+ size 3641876704
Marx-3B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc6eaf5067ef8807d9916b9c3ee84e4fff8c128e79273f782e37c4e4ea20abf
3
+ size 3641876704
README.md ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ datasets:
6
+ - totally-not-an-llm/everything-sharegptformat-morecleaned
7
+ pipeline_tag: text-generation
8
+ tags:
9
+ - TensorBlock
10
+ - GGUF
11
+ base_model: acrastt/Marx-3B
12
+ model-index:
13
+ - name: Marx-3B
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: 43.17
28
+ name: normalized accuracy
29
+ source:
30
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
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: 72.68
44
+ name: normalized accuracy
45
+ source:
46
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
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: 28.46
61
+ name: accuracy
62
+ source:
63
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
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: 39.09
78
+ source:
79
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
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: 65.59
94
+ name: accuracy
95
+ source:
96
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
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: 1.29
111
+ name: accuracy
112
+ source:
113
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/Marx-3B
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
+ ## acrastt/Marx-3B - GGUF
129
+
130
+ This repo contains GGUF format model files for [acrastt/Marx-3B](https://huggingface.co/acrastt/Marx-3B).
131
+
132
+ 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).
133
+
134
+ ## Prompt template
135
+
136
+ ```
137
+
138
+ ```
139
+
140
+ ## Model file specification
141
+
142
+ | Filename | Quant type | File Size | Description |
143
+ | -------- | ---------- | --------- | ----------- |
144
+ | [Marx-3B-Q2_K.gguf](https://huggingface.co/tensorblock/Marx-3B-GGUF/tree/main/Marx-3B-Q2_K.gguf) | Q2_K | 1.844 GB | smallest, significant quality loss - not recommended for most purposes |
145
+ | [Marx-3B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Marx-3B-GGUF/tree/main/Marx-3B-Q3_K_S.gguf) | Q3_K_S | 1.844 GB | very small, high quality loss |
146
+ | [Marx-3B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Marx-3B-GGUF/tree/main/Marx-3B-Q3_K_M.gguf) | Q3_K_M | 1.992 GB | very small, high quality loss |
147
+ | [Marx-3B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Marx-3B-GGUF/tree/main/Marx-3B-Q3_K_L.gguf) | Q3_K_L | 2.062 GB | small, substantial quality loss |
148
+ | [Marx-3B-Q4_0.gguf](https://huggingface.co/tensorblock/Marx-3B-GGUF/tree/main/Marx-3B-Q4_0.gguf) | Q4_0 | 1.844 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
149
+ | [Marx-3B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Marx-3B-GGUF/tree/main/Marx-3B-Q4_K_S.gguf) | Q4_K_S | 2.238 GB | small, greater quality loss |
150
+ | [Marx-3B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Marx-3B-GGUF/tree/main/Marx-3B-Q4_K_M.gguf) | Q4_K_M | 2.403 GB | medium, balanced quality - recommended |
151
+ | [Marx-3B-Q5_0.gguf](https://huggingface.co/tensorblock/Marx-3B-GGUF/tree/main/Marx-3B-Q5_0.gguf) | Q5_0 | 2.231 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
152
+ | [Marx-3B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Marx-3B-GGUF/tree/main/Marx-3B-Q5_K_S.gguf) | Q5_K_S | 2.424 GB | large, low quality loss - recommended |
153
+ | [Marx-3B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Marx-3B-GGUF/tree/main/Marx-3B-Q5_K_M.gguf) | Q5_K_M | 2.568 GB | large, very low quality loss - recommended |
154
+ | [Marx-3B-Q6_K.gguf](https://huggingface.co/tensorblock/Marx-3B-GGUF/tree/main/Marx-3B-Q6_K.gguf) | Q6_K | 3.392 GB | very large, extremely low quality loss |
155
+ | [Marx-3B-Q8_0.gguf](https://huggingface.co/tensorblock/Marx-3B-GGUF/tree/main/Marx-3B-Q8_0.gguf) | Q8_0 | 3.392 GB | very large, extremely low quality loss - not recommended |
156
+
157
+
158
+ ## Downloading instruction
159
+
160
+ ### Command line
161
+
162
+ Firstly, install Huggingface Client
163
+
164
+ ```shell
165
+ pip install -U "huggingface_hub[cli]"
166
+ ```
167
+
168
+ Then, downoad the individual model file the a local directory
169
+
170
+ ```shell
171
+ huggingface-cli download tensorblock/Marx-3B-GGUF --include "Marx-3B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
172
+ ```
173
+
174
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
175
+
176
+ ```shell
177
+ huggingface-cli download tensorblock/Marx-3B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
178
+ ```