morriszms commited on
Commit
28531c1
·
verified ·
1 Parent(s): 6a43326

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
+ Qwen2.5-32B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Qwen2.5-32B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Qwen2.5-32B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Qwen2.5-32B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Qwen2.5-32B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Qwen2.5-32B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Qwen2.5-32B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Qwen2.5-32B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Qwen2.5-32B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Qwen2.5-32B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Qwen2.5-32B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Qwen2.5-32B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-32B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e0bd48eb58e1497f95fc268b2df0eafc4819698cfce69c7d38348c286fbb7d4
3
+ size 12313098464
Qwen2.5-32B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95af346c43adba30066750c0d7810c61e0d0079c18c6f1c10d35747c9bebda51
3
+ size 17247078624
Qwen2.5-32B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:100ce12058e90a98ef3a642242c07cdd2465098c65d88bca7ba6fdd1759ca461
3
+ size 15935047904
Qwen2.5-32B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3197654e1f69cfb3e64e0f0812b89f984584ae236bafd069ec221e38f881c3
3
+ size 14392330464
Qwen2.5-32B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da76a5c5bdb324fa9be9196ed14322f86c81af31b47b07f8a3a2fa0bddef499d
3
+ size 18640230624
Qwen2.5-32B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5207254ba76cc5ce5384e70b09f6216696397525d85b7d9fe320f3d3d6507d31
3
+ size 19851335904
Qwen2.5-32B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac30561c8cc29bd269a7bbf54efd89ace8b41d66036ae723f6ab88911e15e86d
3
+ size 18784409824
Qwen2.5-32B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2080abeb6b21e09182113769ddf24291e63626e1739860a4ce34e29dd957f63b
3
+ size 22638254304
Qwen2.5-32B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5c82619ac665481ffdb71804d0307cdbcce58484c57ffadb45a6d1a9b68d302
3
+ size 23262157024
Qwen2.5-32B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46a974a171aa36d2438feaf1d29ac4c8b3358c2d6e6c202123b20b7facd2f483
3
+ size 22638254304
Qwen2.5-32B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65831a9a48b12e6e596567fd2bc31b79b3eaff814877b473f47b64b470765908
3
+ size 26886154464
Qwen2.5-32B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61b28c12e88cde55b018363f6e97cf6f56a6ac4cf393e72362ee2cfc931a14b9
3
+ size 34820884704
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ license_link: https://huggingface.co/Qwen/Qwen2.5-32B/blob/main/LICENSE
4
+ language:
5
+ - en
6
+ pipeline_tag: text-generation
7
+ base_model: Qwen/Qwen2.5-32B
8
+ tags:
9
+ - TensorBlock
10
+ - GGUF
11
+ ---
12
+
13
+ <div style="width: auto; margin-left: auto; margin-right: auto">
14
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
+ </div>
16
+ <div style="display: flex; justify-content: space-between; width: 100%;">
17
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
18
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
19
+ 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>
20
+ </p>
21
+ </div>
22
+ </div>
23
+
24
+ ## Qwen/Qwen2.5-32B - GGUF
25
+
26
+ This repo contains GGUF format model files for [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B).
27
+
28
+ 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).
29
+
30
+ ## Prompt template
31
+
32
+ ```
33
+ <|im_start|>system
34
+ {system_prompt}<|im_end|>
35
+ <|im_start|>user
36
+ {prompt}<|im_end|>
37
+ <|im_start|>assistant
38
+ ```
39
+
40
+ ## Model file specification
41
+
42
+ | Filename | Quant type | File Size | Description |
43
+ | -------- | ---------- | --------- | ----------- |
44
+ | [Qwen2.5-32B-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-GGUF/tree/main/Qwen2.5-32B-Q2_K.gguf) | Q2_K | 11.467 GB | smallest, significant quality loss - not recommended for most purposes |
45
+ | [Qwen2.5-32B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-GGUF/tree/main/Qwen2.5-32B-Q3_K_S.gguf) | Q3_K_S | 13.404 GB | very small, high quality loss |
46
+ | [Qwen2.5-32B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-GGUF/tree/main/Qwen2.5-32B-Q3_K_M.gguf) | Q3_K_M | 14.841 GB | very small, high quality loss |
47
+ | [Qwen2.5-32B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-GGUF/tree/main/Qwen2.5-32B-Q3_K_L.gguf) | Q3_K_L | 16.063 GB | small, substantial quality loss |
48
+ | [Qwen2.5-32B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-GGUF/tree/main/Qwen2.5-32B-Q4_0.gguf) | Q4_0 | 17.360 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
49
+ | [Qwen2.5-32B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-GGUF/tree/main/Qwen2.5-32B-Q4_K_S.gguf) | Q4_K_S | 17.494 GB | small, greater quality loss |
50
+ | [Qwen2.5-32B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-GGUF/tree/main/Qwen2.5-32B-Q4_K_M.gguf) | Q4_K_M | 18.488 GB | medium, balanced quality - recommended |
51
+ | [Qwen2.5-32B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-GGUF/tree/main/Qwen2.5-32B-Q5_0.gguf) | Q5_0 | 21.084 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
52
+ | [Qwen2.5-32B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-GGUF/tree/main/Qwen2.5-32B-Q5_K_S.gguf) | Q5_K_S | 21.084 GB | large, low quality loss - recommended |
53
+ | [Qwen2.5-32B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-GGUF/tree/main/Qwen2.5-32B-Q5_K_M.gguf) | Q5_K_M | 21.665 GB | large, very low quality loss - recommended |
54
+ | [Qwen2.5-32B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-GGUF/tree/main/Qwen2.5-32B-Q6_K.gguf) | Q6_K | 25.040 GB | very large, extremely low quality loss |
55
+ | [Qwen2.5-32B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-GGUF/tree/main/Qwen2.5-32B-Q8_0.gguf) | Q8_0 | 32.429 GB | very large, extremely low quality loss - not recommended |
56
+
57
+
58
+ ## Downloading instruction
59
+
60
+ ### Command line
61
+
62
+ Firstly, install Huggingface Client
63
+
64
+ ```shell
65
+ pip install -U "huggingface_hub[cli]"
66
+ ```
67
+
68
+ Then, downoad the individual model file the a local directory
69
+
70
+ ```shell
71
+ huggingface-cli download tensorblock/Qwen2.5-32B-GGUF --include "Qwen2.5-32B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
72
+ ```
73
+
74
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
75
+
76
+ ```shell
77
+ huggingface-cli download tensorblock/Qwen2.5-32B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
78
+ ```