GGUF
Korean
math
TensorBlock
GGUF
Eval Results
conversational
morriszms commited on
Commit
4de90c4
·
verified ·
1 Parent(s): 6d21722

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
+ EEVE-Math-10.8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ EEVE-Math-10.8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ EEVE-Math-10.8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ EEVE-Math-10.8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ EEVE-Math-10.8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ EEVE-Math-10.8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ EEVE-Math-10.8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ EEVE-Math-10.8B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ EEVE-Math-10.8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ EEVE-Math-10.8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ EEVE-Math-10.8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ EEVE-Math-10.8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
EEVE-Math-10.8B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3b0934d4e5bbafdd93bddd90910ba647600af444ed5ed613d7d243b312c8dad
3
+ size 4045599456
EEVE-Math-10.8B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53b29c32b3e86f1727794ecd690304a22c288cc123c353fc50ef241a49a84ded
3
+ size 5696844512
EEVE-Math-10.8B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49fac4f35dfe63c47583a87665e9182126b478068787ec816c9a5dcf8675df7a
3
+ size 5241762528
EEVE-Math-10.8B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8955aa4206b99a207078e72a4542d201c1fc8b225808266d061d82940cb3e205
3
+ size 4710658784
EEVE-Math-10.8B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd6d691bffc82d0784666d08c213339d29091c11339fd9f8e5aa82a58763ac2
3
+ size 6123352800
EEVE-Math-10.8B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37cd935ec8b101ae4fd90b9cee49ad896f587d2f7a03afa59cbb93ceb862d3fe
3
+ size 6512636640
EEVE-Math-10.8B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d3d9762f4fa78be054c9438fa8e43e0a10e9a1d4e567a756710127233e0b4d1
3
+ size 6169490144
EEVE-Math-10.8B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c436080559dba22b460ad5d84257d6fbc571ef4167bec24bbbfd1bbaa2d8879c
3
+ size 7452947168
EEVE-Math-10.8B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf029ed602c5049c4a511131728f49203fe786defbc67d19a24866bfa4ad937
3
+ size 7653487328
EEVE-Math-10.8B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8fa95d986b90c1be7e215b265fc5654a41d011ce0bc5c15f9c709b2e5ae8a7e
3
+ size 7452947168
EEVE-Math-10.8B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a2429e7c679011b9f0b333f4fbfc6dd740d77d20d4ef9dd07631d4fe93432e1
3
+ size 8865641184
EEVE-Math-10.8B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b639618690902d057c5b717149308de207234f703b4ee6dbcb16b2529436128
3
+ size 11482362592
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: kuotient/EEVE-Math-10.8B
3
+ license: cc-by-sa-4.0
4
+ language:
5
+ - ko
6
+ tags:
7
+ - math
8
+ - TensorBlock
9
+ - GGUF
10
+ datasets:
11
+ - kuotient/orca-math-word-problems-193k-korean
12
+ model-index:
13
+ - name: EEVE-Math-10.8B
14
+ results:
15
+ - task:
16
+ type: text-generation
17
+ dataset:
18
+ name: gsm8k-ko
19
+ type: gsm8k
20
+ metrics:
21
+ - type: pass@1
22
+ value: 0.539
23
+ name: pass@1
24
+ verified: false
25
+ ---
26
+
27
+ <div style="width: auto; margin-left: auto; margin-right: auto">
28
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
29
+ </div>
30
+ <div style="display: flex; justify-content: space-between; width: 100%;">
31
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
32
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
33
+ 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>
34
+ </p>
35
+ </div>
36
+ </div>
37
+
38
+ ## kuotient/EEVE-Math-10.8B - GGUF
39
+
40
+ This repo contains GGUF format model files for [kuotient/EEVE-Math-10.8B](https://huggingface.co/kuotient/EEVE-Math-10.8B).
41
+
42
+ 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).
43
+
44
+ <div style="text-align: left; margin: 20px 0;">
45
+ <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;">
46
+ Run them on the TensorBlock client using your local machine ↗
47
+ </a>
48
+ </div>
49
+
50
+ ## Prompt template
51
+
52
+ ```
53
+ <|im_start|>system
54
+ {system_prompt}<|im_end|>
55
+ <|im_start|>user
56
+ {prompt}<|im_end|>
57
+ <|im_start|>assistant
58
+ ```
59
+
60
+ ## Model file specification
61
+
62
+ | Filename | Quant type | File Size | Description |
63
+ | -------- | ---------- | --------- | ----------- |
64
+ | [EEVE-Math-10.8B-Q2_K.gguf](https://huggingface.co/tensorblock/EEVE-Math-10.8B-GGUF/blob/main/EEVE-Math-10.8B-Q2_K.gguf) | Q2_K | 4.046 GB | smallest, significant quality loss - not recommended for most purposes |
65
+ | [EEVE-Math-10.8B-Q3_K_S.gguf](https://huggingface.co/tensorblock/EEVE-Math-10.8B-GGUF/blob/main/EEVE-Math-10.8B-Q3_K_S.gguf) | Q3_K_S | 4.711 GB | very small, high quality loss |
66
+ | [EEVE-Math-10.8B-Q3_K_M.gguf](https://huggingface.co/tensorblock/EEVE-Math-10.8B-GGUF/blob/main/EEVE-Math-10.8B-Q3_K_M.gguf) | Q3_K_M | 5.242 GB | very small, high quality loss |
67
+ | [EEVE-Math-10.8B-Q3_K_L.gguf](https://huggingface.co/tensorblock/EEVE-Math-10.8B-GGUF/blob/main/EEVE-Math-10.8B-Q3_K_L.gguf) | Q3_K_L | 5.697 GB | small, substantial quality loss |
68
+ | [EEVE-Math-10.8B-Q4_0.gguf](https://huggingface.co/tensorblock/EEVE-Math-10.8B-GGUF/blob/main/EEVE-Math-10.8B-Q4_0.gguf) | Q4_0 | 6.123 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
69
+ | [EEVE-Math-10.8B-Q4_K_S.gguf](https://huggingface.co/tensorblock/EEVE-Math-10.8B-GGUF/blob/main/EEVE-Math-10.8B-Q4_K_S.gguf) | Q4_K_S | 6.169 GB | small, greater quality loss |
70
+ | [EEVE-Math-10.8B-Q4_K_M.gguf](https://huggingface.co/tensorblock/EEVE-Math-10.8B-GGUF/blob/main/EEVE-Math-10.8B-Q4_K_M.gguf) | Q4_K_M | 6.513 GB | medium, balanced quality - recommended |
71
+ | [EEVE-Math-10.8B-Q5_0.gguf](https://huggingface.co/tensorblock/EEVE-Math-10.8B-GGUF/blob/main/EEVE-Math-10.8B-Q5_0.gguf) | Q5_0 | 7.453 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
72
+ | [EEVE-Math-10.8B-Q5_K_S.gguf](https://huggingface.co/tensorblock/EEVE-Math-10.8B-GGUF/blob/main/EEVE-Math-10.8B-Q5_K_S.gguf) | Q5_K_S | 7.453 GB | large, low quality loss - recommended |
73
+ | [EEVE-Math-10.8B-Q5_K_M.gguf](https://huggingface.co/tensorblock/EEVE-Math-10.8B-GGUF/blob/main/EEVE-Math-10.8B-Q5_K_M.gguf) | Q5_K_M | 7.653 GB | large, very low quality loss - recommended |
74
+ | [EEVE-Math-10.8B-Q6_K.gguf](https://huggingface.co/tensorblock/EEVE-Math-10.8B-GGUF/blob/main/EEVE-Math-10.8B-Q6_K.gguf) | Q6_K | 8.866 GB | very large, extremely low quality loss |
75
+ | [EEVE-Math-10.8B-Q8_0.gguf](https://huggingface.co/tensorblock/EEVE-Math-10.8B-GGUF/blob/main/EEVE-Math-10.8B-Q8_0.gguf) | Q8_0 | 11.482 GB | very large, extremely low quality loss - not recommended |
76
+
77
+
78
+ ## Downloading instruction
79
+
80
+ ### Command line
81
+
82
+ Firstly, install Huggingface Client
83
+
84
+ ```shell
85
+ pip install -U "huggingface_hub[cli]"
86
+ ```
87
+
88
+ Then, downoad the individual model file the a local directory
89
+
90
+ ```shell
91
+ huggingface-cli download tensorblock/EEVE-Math-10.8B-GGUF --include "EEVE-Math-10.8B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
92
+ ```
93
+
94
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
95
+
96
+ ```shell
97
+ huggingface-cli download tensorblock/EEVE-Math-10.8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
98
+ ```