Hugging Face's logo

tensorblock
/
deepseekmath-7b-sft-MATH-v2-GGUF

Transformers
GGUF
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
morriszms commited on
Commit
8866862
•
1 Parent(s): e095e34

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +76 -0
  3. deepseekmath-7b-sft-MATH-v2-Q2_K.gguf +3 -0
  4. deepseekmath-7b-sft-MATH-v2-Q3_K_L.gguf +3 -0
  5. deepseekmath-7b-sft-MATH-v2-Q3_K_M.gguf +3 -0
  6. deepseekmath-7b-sft-MATH-v2-Q3_K_S.gguf +3 -0
  7. deepseekmath-7b-sft-MATH-v2-Q4_0.gguf +3 -0
  8. deepseekmath-7b-sft-MATH-v2-Q4_K_M.gguf +3 -0
  9. deepseekmath-7b-sft-MATH-v2-Q4_K_S.gguf +3 -0
  10. deepseekmath-7b-sft-MATH-v2-Q5_0.gguf +3 -0
  11. deepseekmath-7b-sft-MATH-v2-Q5_K_M.gguf +3 -0
  12. deepseekmath-7b-sft-MATH-v2-Q5_K_S.gguf +3 -0
  13. deepseekmath-7b-sft-MATH-v2-Q6_K.gguf +3 -0
  14. deepseekmath-7b-sft-MATH-v2-Q8_0.gguf +3 -0
.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
+ deepseekmath-7b-sft-MATH-v2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ deepseekmath-7b-sft-MATH-v2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ deepseekmath-7b-sft-MATH-v2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ deepseekmath-7b-sft-MATH-v2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ deepseekmath-7b-sft-MATH-v2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ deepseekmath-7b-sft-MATH-v2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ deepseekmath-7b-sft-MATH-v2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ deepseekmath-7b-sft-MATH-v2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ deepseekmath-7b-sft-MATH-v2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ deepseekmath-7b-sft-MATH-v2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ deepseekmath-7b-sft-MATH-v2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ deepseekmath-7b-sft-MATH-v2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - TensorBlock
5
+ - GGUF
6
+ base_model: realtreetune/deepseekmath-7b-sft-MATH-v2
7
+ ---
8
+
9
+ <div style="width: auto; margin-left: auto; margin-right: auto">
10
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
11
+ </div>
12
+ <div style="display: flex; justify-content: space-between; width: 100%;">
13
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
14
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
15
+ 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>
16
+ </p>
17
+ </div>
18
+ </div>
19
+
20
+ ## realtreetune/deepseekmath-7b-sft-MATH-v2 - GGUF
21
+
22
+ This repo contains GGUF format model files for [realtreetune/deepseekmath-7b-sft-MATH-v2](https://huggingface.co/realtreetune/deepseekmath-7b-sft-MATH-v2).
23
+
24
+ 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).
25
+
26
+ <div style="text-align: left; margin: 20px 0;">
27
+ <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;">
28
+ Run them on the TensorBlock client using your local machine ↗
29
+ </a>
30
+ </div>
31
+
32
+ ## Prompt template
33
+
34
+ ```
35
+
36
+ ```
37
+
38
+ ## Model file specification
39
+
40
+ | Filename | Quant type | File Size | Description |
41
+ | -------- | ---------- | --------- | ----------- |
42
+ | [deepseekmath-7b-sft-MATH-v2-Q2_K.gguf](https://huggingface.co/tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF/blob/main/deepseekmath-7b-sft-MATH-v2-Q2_K.gguf) | Q2_K | 2.532 GB | smallest, significant quality loss - not recommended for most purposes |
43
+ | [deepseekmath-7b-sft-MATH-v2-Q3_K_S.gguf](https://huggingface.co/tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF/blob/main/deepseekmath-7b-sft-MATH-v2-Q3_K_S.gguf) | Q3_K_S | 2.923 GB | very small, high quality loss |
44
+ | [deepseekmath-7b-sft-MATH-v2-Q3_K_M.gguf](https://huggingface.co/tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF/blob/main/deepseekmath-7b-sft-MATH-v2-Q3_K_M.gguf) | Q3_K_M | 3.223 GB | very small, high quality loss |
45
+ | [deepseekmath-7b-sft-MATH-v2-Q3_K_L.gguf](https://huggingface.co/tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF/blob/main/deepseekmath-7b-sft-MATH-v2-Q3_K_L.gguf) | Q3_K_L | 3.489 GB | small, substantial quality loss |
46
+ | [deepseekmath-7b-sft-MATH-v2-Q4_0.gguf](https://huggingface.co/tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF/blob/main/deepseekmath-7b-sft-MATH-v2-Q4_0.gguf) | Q4_0 | 3.725 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
47
+ | [deepseekmath-7b-sft-MATH-v2-Q4_K_S.gguf](https://huggingface.co/tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF/blob/main/deepseekmath-7b-sft-MATH-v2-Q4_K_S.gguf) | Q4_K_S | 3.749 GB | small, greater quality loss |
48
+ | [deepseekmath-7b-sft-MATH-v2-Q4_K_M.gguf](https://huggingface.co/tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF/blob/main/deepseekmath-7b-sft-MATH-v2-Q4_K_M.gguf) | Q4_K_M | 3.933 GB | medium, balanced quality - recommended |
49
+ | [deepseekmath-7b-sft-MATH-v2-Q5_0.gguf](https://huggingface.co/tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF/blob/main/deepseekmath-7b-sft-MATH-v2-Q5_0.gguf) | Q5_0 | 4.481 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
50
+ | [deepseekmath-7b-sft-MATH-v2-Q5_K_S.gguf](https://huggingface.co/tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF/blob/main/deepseekmath-7b-sft-MATH-v2-Q5_K_S.gguf) | Q5_K_S | 4.481 GB | large, low quality loss - recommended |
51
+ | [deepseekmath-7b-sft-MATH-v2-Q5_K_M.gguf](https://huggingface.co/tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF/blob/main/deepseekmath-7b-sft-MATH-v2-Q5_K_M.gguf) | Q5_K_M | 4.588 GB | large, very low quality loss - recommended |
52
+ | [deepseekmath-7b-sft-MATH-v2-Q6_K.gguf](https://huggingface.co/tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF/blob/main/deepseekmath-7b-sft-MATH-v2-Q6_K.gguf) | Q6_K | 5.284 GB | very large, extremely low quality loss |
53
+ | [deepseekmath-7b-sft-MATH-v2-Q8_0.gguf](https://huggingface.co/tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF/blob/main/deepseekmath-7b-sft-MATH-v2-Q8_0.gguf) | Q8_0 | 6.842 GB | very large, extremely low quality loss - not recommended |
54
+
55
+
56
+ ## Downloading instruction
57
+
58
+ ### Command line
59
+
60
+ Firstly, install Huggingface Client
61
+
62
+ ```shell
63
+ pip install -U "huggingface_hub[cli]"
64
+ ```
65
+
66
+ Then, downoad the individual model file the a local directory
67
+
68
+ ```shell
69
+ huggingface-cli download tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF --include "deepseekmath-7b-sft-MATH-v2-Q2_K.gguf" --local-dir MY_LOCAL_DIR
70
+ ```
71
+
72
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
73
+
74
+ ```shell
75
+ huggingface-cli download tensorblock/deepseekmath-7b-sft-MATH-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
76
+ ```
deepseekmath-7b-sft-MATH-v2-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce5ada8bdd06b3e687b352698384e26fdb61015b9c762012a405b5d8c63a055
3
+ size 2718422336
deepseekmath-7b-sft-MATH-v2-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b064c3411983557839e1e4ee1fe085bdfd62593d46079d3e44bcadacccb3ef73
3
+ size 3746272576
deepseekmath-7b-sft-MATH-v2-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb604641abfc97a763806301647b80f865e528e546501dbe15c59d95480f6ee
3
+ size 3461190976
deepseekmath-7b-sft-MATH-v2-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8a695d6cc7a394a5db020c487a4b51014963273c4da1a86b733e36ba8c354c1
3
+ size 3138016576
deepseekmath-7b-sft-MATH-v2-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef2d94d59e1404c6320bb41fa61f127d7af098cd8c52ac22f82e6fec9d0247e
3
+ size 4000060736
deepseekmath-7b-sft-MATH-v2-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2d30df4d06ad4e35cb245e6d525ea05bd810b2e8ab1339d507692100e2889b4
3
+ size 4223358272
deepseekmath-7b-sft-MATH-v2-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3d2f937eec866b26322a5128201a5dd41cc1f8b4c63f018f835ab4eba3fd7f0
3
+ size 4025357632
deepseekmath-7b-sft-MATH-v2-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e206a8bd3872d0b1e88549b65adcf2dfd38f4f7702ad6045ffb8b4b495b280
3
+ size 4811396416
deepseekmath-7b-sft-MATH-v2-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef088d3db0dd2ce684c771bfa893dc3c915984812b126581c4bbdc561ce0e21
3
+ size 4926428480
deepseekmath-7b-sft-MATH-v2-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a7b2c24f14e1b3c96d5d0389405d7ce910166c5a58accfb724141b945c673d8
3
+ size 4811396416
deepseekmath-7b-sft-MATH-v2-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f71f24c721cc96f5dcbe59c91957f3e73523378194a20a3c8f8f40707dbbcb9
3
+ size 5673440576
deepseekmath-7b-sft-MATH-v2-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69d8fab6b0a93f7a3e49b0237db13e826c55deb1e7c237ac3a33620edc95acb2
3
+ size 7346984256