morriszms commited on
Commit
f6362ea
·
verified ·
1 Parent(s): adcd470

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-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Qwen2.5-Coder-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Qwen2.5-Coder-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Qwen2.5-Coder-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Qwen2.5-Coder-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Qwen2.5-Coder-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Qwen2.5-Coder-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Qwen2.5-Coder-3B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Qwen2.5-Coder-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Qwen2.5-Coder-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Qwen2.5-Coder-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Qwen2.5-Coder-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-Coder-3B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2af21150f688c4a2579da215797c5705524c639de8e05837b1a3a2021fdc7435
3
+ size 1274755936
Qwen2.5-Coder-3B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:754da7357b3410392325d71e7ef9f61f216edae254bd9c2fd221e92a22037f0c
3
+ size 1707391840
Qwen2.5-Coder-3B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe0728bd682b3244d2afebcd1d0da26bc63819a309d2418769bc59048f474d5b
3
+ size 1590475616
Qwen2.5-Coder-3B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a2ce48d026c77dc74fec566d8976966ec5a092710bced6a496fbe1d22d489c8
3
+ size 1454357344
Qwen2.5-Coder-3B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df308b6c26c696aa34a3da8a868fa72594b63937b60bf9c9f50a2db2403bf9cb
3
+ size 1822849888
Qwen2.5-Coder-3B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:433d2d9314aed9ec99b62c2f138a79cba33673e85d5ecc36358efbb499977341
3
+ size 1929902944
Qwen2.5-Coder-3B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3ec9355c591642365ba59b5adb6d5e812b3fc2c96c6f53e83c67eea1fec232c
3
+ size 1834384224
Qwen2.5-Coder-3B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2467ea1e621769f4234527b3ba8ecdbd34f2a9141fe8981f5bfe49662472d102
3
+ size 2169666400
Qwen2.5-Coder-3B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:866ef7447348825750bf101652d6d112219fee8fbb206ea9874c9e97d8e6d8ec
3
+ size 2224814944
Qwen2.5-Coder-3B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:452f3e9d6bb1346e723c4fc7173017f658c66172ea77da8dd722936b021080ca
3
+ size 2169666400
Qwen2.5-Coder-3B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a1df0d9a87c7210d5c7171faff1ba5ad912fdab2a4d8104db2d95f234f53ad
3
+ size 2538158944
Qwen2.5-Coder-3B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9622fc8e5103999005f2291db8f488ce1ea22f748502072d7537de1e5d7cc6f7
3
+ size 3285476192
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: qwen-research
4
+ license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-3B/blob/main/LICENSE
5
+ language:
6
+ - en
7
+ base_model: Qwen/Qwen2.5-Coder-3B
8
+ pipeline_tag: text-generation
9
+ library_name: transformers
10
+ tags:
11
+ - code
12
+ - qwen
13
+ - qwen-coder
14
+ - codeqwen
15
+ - TensorBlock
16
+ - GGUF
17
+ ---
18
+
19
+ <div style="width: auto; margin-left: auto; margin-right: auto">
20
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
21
+ </div>
22
+ <div style="display: flex; justify-content: space-between; width: 100%;">
23
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
24
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
25
+ 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>
26
+ </p>
27
+ </div>
28
+ </div>
29
+
30
+ ## Qwen/Qwen2.5-Coder-3B - GGUF
31
+
32
+ This repo contains GGUF format model files for [Qwen/Qwen2.5-Coder-3B](https://huggingface.co/Qwen/Qwen2.5-Coder-3B).
33
+
34
+ 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).
35
+
36
+ <div style="text-align: left; margin: 20px 0;">
37
+ <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;">
38
+ Run them on the TensorBlock client using your local machine ↗
39
+ </a>
40
+ </div>
41
+
42
+ ## Prompt template
43
+
44
+ ```
45
+ <|im_start|>system
46
+ {system_prompt}<|im_end|>
47
+ <|im_start|>user
48
+ {prompt}<|im_end|>
49
+ <|im_start|>assistant
50
+ ```
51
+
52
+ ## Model file specification
53
+
54
+ | Filename | Quant type | File Size | Description |
55
+ | -------- | ---------- | --------- | ----------- |
56
+ | [Qwen2.5-Coder-3B-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-3B-GGUF/blob/main/Qwen2.5-Coder-3B-Q2_K.gguf) | Q2_K | 1.275 GB | smallest, significant quality loss - not recommended for most purposes |
57
+ | [Qwen2.5-Coder-3B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-3B-GGUF/blob/main/Qwen2.5-Coder-3B-Q3_K_S.gguf) | Q3_K_S | 1.454 GB | very small, high quality loss |
58
+ | [Qwen2.5-Coder-3B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-3B-GGUF/blob/main/Qwen2.5-Coder-3B-Q3_K_M.gguf) | Q3_K_M | 1.590 GB | very small, high quality loss |
59
+ | [Qwen2.5-Coder-3B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-3B-GGUF/blob/main/Qwen2.5-Coder-3B-Q3_K_L.gguf) | Q3_K_L | 1.707 GB | small, substantial quality loss |
60
+ | [Qwen2.5-Coder-3B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-3B-GGUF/blob/main/Qwen2.5-Coder-3B-Q4_0.gguf) | Q4_0 | 1.823 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
61
+ | [Qwen2.5-Coder-3B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-3B-GGUF/blob/main/Qwen2.5-Coder-3B-Q4_K_S.gguf) | Q4_K_S | 1.834 GB | small, greater quality loss |
62
+ | [Qwen2.5-Coder-3B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-3B-GGUF/blob/main/Qwen2.5-Coder-3B-Q4_K_M.gguf) | Q4_K_M | 1.930 GB | medium, balanced quality - recommended |
63
+ | [Qwen2.5-Coder-3B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-3B-GGUF/blob/main/Qwen2.5-Coder-3B-Q5_0.gguf) | Q5_0 | 2.170 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
64
+ | [Qwen2.5-Coder-3B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-3B-GGUF/blob/main/Qwen2.5-Coder-3B-Q5_K_S.gguf) | Q5_K_S | 2.170 GB | large, low quality loss - recommended |
65
+ | [Qwen2.5-Coder-3B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-3B-GGUF/blob/main/Qwen2.5-Coder-3B-Q5_K_M.gguf) | Q5_K_M | 2.225 GB | large, very low quality loss - recommended |
66
+ | [Qwen2.5-Coder-3B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-3B-GGUF/blob/main/Qwen2.5-Coder-3B-Q6_K.gguf) | Q6_K | 2.538 GB | very large, extremely low quality loss |
67
+ | [Qwen2.5-Coder-3B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-Coder-3B-GGUF/blob/main/Qwen2.5-Coder-3B-Q8_0.gguf) | Q8_0 | 3.285 GB | very large, extremely low quality loss - not recommended |
68
+
69
+
70
+ ## Downloading instruction
71
+
72
+ ### Command line
73
+
74
+ Firstly, install Huggingface Client
75
+
76
+ ```shell
77
+ pip install -U "huggingface_hub[cli]"
78
+ ```
79
+
80
+ Then, downoad the individual model file the a local directory
81
+
82
+ ```shell
83
+ huggingface-cli download tensorblock/Qwen2.5-Coder-3B-GGUF --include "Qwen2.5-Coder-3B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
84
+ ```
85
+
86
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
87
+
88
+ ```shell
89
+ huggingface-cli download tensorblock/Qwen2.5-Coder-3B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
90
+ ```