morriszms commited on
Commit
c95fc0d
1 Parent(s): ecd5218

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
+ Qwen1.5-4B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Qwen1.5-4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Qwen1.5-4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Qwen1.5-4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Qwen1.5-4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Qwen1.5-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Qwen1.5-4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Qwen1.5-4B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Qwen1.5-4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Qwen1.5-4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Qwen1.5-4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Qwen1.5-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen1.5-4B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4fbee1d9ff098a32128636a56507b4648ecec99db33ea8406a3df223dc15a04
3
+ size 1620633248
Qwen1.5-4B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc65c6432288e045ae2dcee404a2dd2b5a5ec70b955c4e013443c3c7b324289
3
+ size 2174799008
Qwen1.5-4B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7b73031813c058dea85f800ddfc0a588115485af17b9b3109e2e0fea462873e
3
+ size 2026851488
Qwen1.5-4B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94a66622765986738fda057fe63f0812affa0102c16cd3a2f1818fc4e798b02f
3
+ size 1857154208
Qwen1.5-4B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:302d1d732c1b6c7c3ff1d02b77de5c14a93473d869162e38d8a83371d7590454
3
+ size 2330086048
Qwen1.5-4B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296c599d0555a71744a763afa1a7846a55cde7f67799a03035c3cad41d1314a7
3
+ size 2455116448
Qwen1.5-4B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c40d84675dc59773923a8a89f54f66260ec011db5c905da34e8e6ffd1688217
3
+ size 2344422048
Qwen1.5-4B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dce53cb64d29b695b58137217521047752b66dfbdcae6776a9ae925e53ddeee
3
+ size 2775198368
Qwen1.5-4B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2d3d7551805f9baa78f61371aff27da77442a30a334471cc6d0bdde70f60322
3
+ size 2839607968
Qwen1.5-4B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d392a22eb2ef72d959342cbc352e9ddb6720a6d37684896e2d1efef44dd19b
3
+ size 2775198368
Qwen1.5-4B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ab05f562595b1618fc1ce63ae25b5c95527bfedbd8c32fb80dc193f28c968c4
3
+ size 3248130208
Qwen1.5-4B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667c8bb42db1e1c1b45c2ed2ddbfcc4e4824098067995821889e1f35fae97a5
3
+ size 4204735648
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: tongyi-qianwen-research
4
+ license_link: https://huggingface.co/Qwen/Qwen1.5-4B/blob/main/LICENSE
5
+ language:
6
+ - en
7
+ pipeline_tag: text-generation
8
+ tags:
9
+ - pretrained
10
+ - TensorBlock
11
+ - GGUF
12
+ base_model: Qwen/Qwen1.5-4B
13
+ ---
14
+
15
+ <div style="width: auto; margin-left: auto; margin-right: auto">
16
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
17
+ </div>
18
+ <div style="display: flex; justify-content: space-between; width: 100%;">
19
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
20
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
21
+ 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>
22
+ </p>
23
+ </div>
24
+ </div>
25
+
26
+ ## Qwen/Qwen1.5-4B - GGUF
27
+
28
+ This repo contains GGUF format model files for [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B).
29
+
30
+ 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).
31
+
32
+ ## Prompt template
33
+
34
+ ```
35
+ <|im_start|>system
36
+ {system_prompt}<|im_end|>
37
+ <|im_start|>user
38
+ {prompt}<|im_end|>
39
+ <|im_start|>assistant
40
+ ```
41
+
42
+ ## Model file specification
43
+
44
+ | Filename | Quant type | File Size | Description |
45
+ | -------- | ---------- | --------- | ----------- |
46
+ | [Qwen1.5-4B-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen1.5-4B-GGUF/tree/main/Qwen1.5-4B-Q2_K.gguf) | Q2_K | 1.509 GB | smallest, significant quality loss - not recommended for most purposes |
47
+ | [Qwen1.5-4B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-4B-GGUF/tree/main/Qwen1.5-4B-Q3_K_S.gguf) | Q3_K_S | 1.730 GB | very small, high quality loss |
48
+ | [Qwen1.5-4B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-4B-GGUF/tree/main/Qwen1.5-4B-Q3_K_M.gguf) | Q3_K_M | 1.888 GB | very small, high quality loss |
49
+ | [Qwen1.5-4B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen1.5-4B-GGUF/tree/main/Qwen1.5-4B-Q3_K_L.gguf) | Q3_K_L | 2.025 GB | small, substantial quality loss |
50
+ | [Qwen1.5-4B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-4B-GGUF/tree/main/Qwen1.5-4B-Q4_0.gguf) | Q4_0 | 2.170 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
51
+ | [Qwen1.5-4B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-4B-GGUF/tree/main/Qwen1.5-4B-Q4_K_S.gguf) | Q4_K_S | 2.183 GB | small, greater quality loss |
52
+ | [Qwen1.5-4B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-4B-GGUF/tree/main/Qwen1.5-4B-Q4_K_M.gguf) | Q4_K_M | 2.287 GB | medium, balanced quality - recommended |
53
+ | [Qwen1.5-4B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-4B-GGUF/tree/main/Qwen1.5-4B-Q5_0.gguf) | Q5_0 | 2.585 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
54
+ | [Qwen1.5-4B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-4B-GGUF/tree/main/Qwen1.5-4B-Q5_K_S.gguf) | Q5_K_S | 2.585 GB | large, low quality loss - recommended |
55
+ | [Qwen1.5-4B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-4B-GGUF/tree/main/Qwen1.5-4B-Q5_K_M.gguf) | Q5_K_M | 2.645 GB | large, very low quality loss - recommended |
56
+ | [Qwen1.5-4B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen1.5-4B-GGUF/tree/main/Qwen1.5-4B-Q6_K.gguf) | Q6_K | 3.025 GB | very large, extremely low quality loss |
57
+ | [Qwen1.5-4B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-4B-GGUF/tree/main/Qwen1.5-4B-Q8_0.gguf) | Q8_0 | 3.916 GB | very large, extremely low quality loss - not recommended |
58
+
59
+
60
+ ## Downloading instruction
61
+
62
+ ### Command line
63
+
64
+ Firstly, install Huggingface Client
65
+
66
+ ```shell
67
+ pip install -U "huggingface_hub[cli]"
68
+ ```
69
+
70
+ Then, downoad the individual model file the a local directory
71
+
72
+ ```shell
73
+ huggingface-cli download tensorblock/Qwen1.5-4B-GGUF --include "Qwen1.5-4B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
74
+ ```
75
+
76
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
77
+
78
+ ```shell
79
+ huggingface-cli download tensorblock/Qwen1.5-4B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
80
+ ```