morriszms commited on
Commit
ac0f615
·
verified ·
1 Parent(s): 56ed08f

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-Coder-32B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Qwen2.5-Coder-32B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Qwen2.5-Coder-32B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Qwen2.5-Coder-32B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Qwen2.5-Coder-32B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Qwen2.5-Coder-32B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Qwen2.5-Coder-32B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Qwen2.5-Coder-32B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Qwen2.5-Coder-32B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Qwen2.5-Coder-32B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Qwen2.5-Coder-32B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Qwen2.5-Coder-32B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-32B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2bb4b025e852a6c26ceb499b16068817440b0f187713ee79e181420dc7b1fc9
3
+ size 12313098784
Qwen2.5-Coder-32B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3cd781210f60b7f65bfbb2221abb0a2ad24121ae0fc30549620b226a0286cb
3
+ size 17247078944
Qwen2.5-Coder-32B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ef1046b90bf89bac34d279da7f4b063dc9b4a89cd649974f8feafc3d8c2cf4
3
+ size 15935048224
Qwen2.5-Coder-32B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:120890d9d7dbe0ec42de1a1225a89121dbbff6ef4836947c0968f532d87acda5
3
+ size 14392330784
Qwen2.5-Coder-32B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:697625c318e84d4bd8d23a60669c355454497516efc3b3897d4055d20c6448da
3
+ size 18640230944
Qwen2.5-Coder-32B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4f6df247da3ed59d4eb2b2544a9308b2880e5e5271e3cc7ce60e8d13d697bb
3
+ size 19851336224
Qwen2.5-Coder-32B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749ebedea0dc61efabb100d5064e6dbab5092fcd9f5c419f4acf450ec7f34115
3
+ size 18784410144
Qwen2.5-Coder-32B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a542637f5fed3bee6dd092d62a4da1d946c65baf17c9e0722386f31a0602d75c
3
+ size 22638254624
Qwen2.5-Coder-32B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5cb8a3495c83e26d6fd0ed209ecd3d60b3af7cec26ba60360db264722da6bc7
3
+ size 23262157344
Qwen2.5-Coder-32B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80e75da1ceb297ba76af75f776cebb0fb98a87aad1f14c1100e2bdd00e399370
3
+ size 22638254624
Qwen2.5-Coder-32B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623f50d539383452796a508d6d82d603fbec4ce05c3b5f3104ea8896fde6464e
3
+ size 26886154784
Qwen2.5-Coder-32B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f17652e6fa0844c405a5e8a5c673768c6cb8668e8ff86faa8ce31695105b586
3
+ size 34820885024
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-32B/blob/main/LICENSE
4
+ language:
5
+ - en
6
+ base_model: Qwen/Qwen2.5-Coder-32B
7
+ pipeline_tag: text-generation
8
+ library_name: transformers
9
+ tags:
10
+ - code
11
+ - qwen
12
+ - qwen-coder
13
+ - codeqwen
14
+ - TensorBlock
15
+ - GGUF
16
+ ---
17
+
18
+ <div style="width: auto; margin-left: auto; margin-right: auto">
19
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
20
+ </div>
21
+ <div style="display: flex; justify-content: space-between; width: 100%;">
22
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
23
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
24
+ 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>
25
+ </p>
26
+ </div>
27
+ </div>
28
+
29
+ ## Qwen/Qwen2.5-Coder-32B - GGUF
30
+
31
+ This repo contains GGUF format model files for [Qwen/Qwen2.5-Coder-32B](https://huggingface.co/Qwen/Qwen2.5-Coder-32B).
32
+
33
+ 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).
34
+
35
+ <div style="text-align: left; margin: 20px 0;">
36
+ <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;">
37
+ Run them on the TensorBlock client using your local machine ↗
38
+ </a>
39
+ </div>
40
+
41
+ ## Prompt template
42
+
43
+ ```
44
+ <|im_start|>system
45
+ {system_prompt}<|im_end|>
46
+ <|im_start|>user
47
+ {prompt}<|im_end|>
48
+ <|im_start|>assistant
49
+ ```
50
+
51
+ ## Model file specification
52
+
53
+ | Filename | Quant type | File Size | Description |
54
+ | -------- | ---------- | --------- | ----------- |
55
+ | [Qwen2.5-Coder-32B-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q2_K.gguf) | Q2_K | 12.313 GB | smallest, significant quality loss - not recommended for most purposes |
56
+ | [Qwen2.5-Coder-32B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q3_K_S.gguf) | Q3_K_S | 14.392 GB | very small, high quality loss |
57
+ | [Qwen2.5-Coder-32B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q3_K_M.gguf) | Q3_K_M | 15.935 GB | very small, high quality loss |
58
+ | [Qwen2.5-Coder-32B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q3_K_L.gguf) | Q3_K_L | 17.247 GB | small, substantial quality loss |
59
+ | [Qwen2.5-Coder-32B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q4_0.gguf) | Q4_0 | 18.640 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
60
+ | [Qwen2.5-Coder-32B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q4_K_S.gguf) | Q4_K_S | 18.784 GB | small, greater quality loss |
61
+ | [Qwen2.5-Coder-32B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q4_K_M.gguf) | Q4_K_M | 19.851 GB | medium, balanced quality - recommended |
62
+ | [Qwen2.5-Coder-32B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q5_0.gguf) | Q5_0 | 22.638 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
63
+ | [Qwen2.5-Coder-32B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q5_K_S.gguf) | Q5_K_S | 22.638 GB | large, low quality loss - recommended |
64
+ | [Qwen2.5-Coder-32B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q5_K_M.gguf) | Q5_K_M | 23.262 GB | large, very low quality loss - recommended |
65
+ | [Qwen2.5-Coder-32B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q6_K.gguf) | Q6_K | 26.886 GB | very large, extremely low quality loss |
66
+ | [Qwen2.5-Coder-32B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-32B-GGUF/blob/main/Qwen2.5-Coder-32B-Q8_0.gguf) | Q8_0 | 34.821 GB | very large, extremely low quality loss - not recommended |
67
+
68
+
69
+ ## Downloading instruction
70
+
71
+ ### Command line
72
+
73
+ Firstly, install Huggingface Client
74
+
75
+ ```shell
76
+ pip install -U "huggingface_hub[cli]"
77
+ ```
78
+
79
+ Then, downoad the individual model file the a local directory
80
+
81
+ ```shell
82
+ huggingface-cli download tensorblock/Qwen2.5-Coder-32B-GGUF --include "Qwen2.5-Coder-32B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
83
+ ```
84
+
85
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
86
+
87
+ ```shell
88
+ huggingface-cli download tensorblock/Qwen2.5-Coder-32B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
89
+ ```