kasumi-1 commited on
Commit
7e93983
1 Parent(s): 986a732

Upload 5 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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
+ DeepSeek-Prover-V1.5-RL.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ DeepSeek-Prover-V1.5-RL.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
38
+ DeepSeek-Prover-V1.5-RL.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
39
+ DeepSeek-Prover-V1.5-RL.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-Prover-V1.5-RL.Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c2749d53cd18295d11b20bfd2258cdeb1ae893615841e5809fc5f3c3f664997
3
+ size 4223359200
DeepSeek-Prover-V1.5-RL.Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123a07de41a750588d1ae7be60014a8258237aa4d90e92dd88fe111b6166dd5f
3
+ size 4926429408
DeepSeek-Prover-V1.5-RL.Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0426b792bd39e8c515ad07f9f6dc23d5a6d29b23fd5bc15f7615176efa7c2967
3
+ size 5673441504
DeepSeek-Prover-V1.5-RL.Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0f72b33f4901a26cae28f3580f1d81771bfaf9a90f17657b7ee1da656da4198
3
+ size 7346985184
README.md CHANGED
@@ -1,5 +1,53 @@
1
- ---
2
- license: other
3
- license_name: deepseek-license
4
- license_link: LICENSE
5
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: deepseek-ai/DeepSeek-Prover-V1.5-RL
3
+ inference: false
4
+ language:
5
+ - en
6
+ license: other
7
+ license_name: deepseek-license
8
+ license_link: LICENSE
9
+ model_name: DeepSeek Prover V1.5 RL
10
+ ---
11
+ <!-- markdownlint-disable MD041 -->
12
+
13
+ <!-- header start -->
14
+ <!-- 200823 -->
15
+ <div align="center">
16
+ <img src="https://raw.githubusercontent.com/semperai/arbius/master/website/public/logo-square-home.png" alt="Arbius" width="60%">
17
+ </div>
18
+
19
+ <div align="center" style="line-height: 1;">
20
+ <a href="https://arbius.ai/" target="_blank" style="margin: 2px;">Homepage</a>
21
+ -
22
+ <a href="https://t.me/arbius_ai" target="_blank" style="margin: 2px;">Telegram</a>
23
+ -
24
+ <a href="https://twitter.com/arbius_ai" target="_blank" style="margin: 2px;">Twitter</a>
25
+ </div>
26
+
27
+
28
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
29
+ <!-- header end -->
30
+
31
+ # DeepSeek Prover V1.5 RL - GGUF
32
+ - Original model: [DeepSeek Prover V1.5 RL](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V1.5-RL)
33
+
34
+ <!-- description start -->
35
+ ## Description
36
+
37
+ This repo contains GGUF format model files for [DeepSeek Prover V1.5 RL](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V1.5-RL).
38
+
39
+ <!-- README_GGUF.md-provided-files start -->
40
+ ## Provided files
41
+
42
+ | Name | Quant method | Bits |
43
+ | ---- | ---- | ---- |
44
+ | [DeepSeek-Prover-V1.5-RL-GGUF.Q4_K_M.gguf](https://huggingface.co/arbius/DeepSeek-Prover-V1.5-RL-GGUF/blob/main/DeepSeek-Prover-V1.5-RL.Q4_K_M.gguf) | Q4_K_M | 4 |
45
+ | [DeepSeek-Prover-V1.5-RL-GGUF.Q5_K_M.gguf](https://huggingface.co/arbius/DeepSeek-Prover-V1.5-RL-GGUF/blob/main/DeepSeek-Prover-V1.5-RL.Q5_K_M.gguf) | Q5_K_M | 5 |
46
+ | [DeepSeek-Prover-V1.5-RL-GGUF.Q6_K.gguf](https://huggingface.co/arbius/DeepSeek-Prover-V1.5-RL-GGUF/blob/main/DeepSeek-Prover-V1.5-RL.Q6_K.gguf) | Q6_K | 6 |
47
+ | [DeepSeek-Prover-V1.5-RL-GGUF.Q8_0.gguf](https://huggingface.co/arbius/DeepSeek-Prover-V1.5-RL-GGUF/blob/main/DeepSeek-Prover-V1.5-RL.Q8_0.gguf) | Q8_0 | 8 |
48
+
49
+ **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
50
+
51
+
52
+
53
+ <!-- README_GGUF.md-provided-files end -->