Transformers
GGUF
Chinese
English
TensorBlock
GGUF
Inference Endpoints
conversational
morriszms commited on
Commit
8ea1b30
·
verified ·
1 Parent(s): 0b895b7

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-AGI-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Qwen2.5-32B-AGI-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Qwen2.5-32B-AGI-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Qwen2.5-32B-AGI-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Qwen2.5-32B-AGI-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Qwen2.5-32B-AGI-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Qwen2.5-32B-AGI-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Qwen2.5-32B-AGI-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Qwen2.5-32B-AGI-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Qwen2.5-32B-AGI-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Qwen2.5-32B-AGI-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Qwen2.5-32B-AGI-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2.5-32B-AGI-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6549295419fa80ad960c68e9e9aacf94d63e338b7a139ff38715cd8c7b6c842b
3
+ size 12313097568
Qwen2.5-32B-AGI-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a070a1b8d048beb08db3dd80ab2af2985312e975308aed8a9907d0baae03dd90
3
+ size 17247077728
Qwen2.5-32B-AGI-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e71377af2f09743b53c3ac18ddfcc7ff6143063af18371dce95cc724e506fed5
3
+ size 15935047008
Qwen2.5-32B-AGI-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a17ec4925db9b1be50558c116955fa8c97a0a061107e0fce656b9c10cba12ba3
3
+ size 14392329568
Qwen2.5-32B-AGI-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f34ad7f0820dd5a27c0d9fe66066b64c5ab35a50d924618b56a4a205cd7fa40
3
+ size 18640229728
Qwen2.5-32B-AGI-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a85f961859609d95d905ddd71043076baa05e23880fca67d3acc558fbc3e099
3
+ size 19851335008
Qwen2.5-32B-AGI-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c32fbafdac70b77dee8be59619f03a8d0db6625b32c6e01a4578fc61dc077de
3
+ size 18784408928
Qwen2.5-32B-AGI-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e2ee310352b5d841055e8f774968d6c957402943aa6ee26345421cf53252129
3
+ size 22638253408
Qwen2.5-32B-AGI-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d8c4f84dd554672f243569c417f94d3b3e70be42f23b98f3d67aeb7a5cec44
3
+ size 23262156128
Qwen2.5-32B-AGI-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5818c771fd2a6f1c06f0e9d28c87270e4a4b020f37813fa49d2648361a304137
3
+ size 22638253408
Qwen2.5-32B-AGI-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3279c45ce3e79b027b8a85232082add1f8574e0e548c23ce764f378f450ce3f8
3
+ size 26886153568
Qwen2.5-32B-AGI-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa93db23cb19d474d2c2a36eb89024b16d140f4423fe9d088ebd28002f9a9d56
3
+ size 34820883808
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - zh
5
+ - en
6
+ base_model: AiCloser/Qwen2.5-32B-AGI
7
+ datasets:
8
+ - anthracite-org/kalo-opus-instruct-22k-no-refusal
9
+ - unalignment/toxic-dpo-v0.2
10
+ - Orion-zhen/dpo-toxic-zh
11
+ library_name: transformers
12
+ tags:
13
+ - TensorBlock
14
+ - GGUF
15
+ ---
16
+
17
+ <div style="width: auto; margin-left: auto; margin-right: auto">
18
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
19
+ </div>
20
+ <div style="display: flex; justify-content: space-between; width: 100%;">
21
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
22
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
23
+ 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>
24
+ </p>
25
+ </div>
26
+ </div>
27
+
28
+ ## AiCloser/Qwen2.5-32B-AGI - GGUF
29
+
30
+ This repo contains GGUF format model files for [AiCloser/Qwen2.5-32B-AGI](https://huggingface.co/AiCloser/Qwen2.5-32B-AGI).
31
+
32
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
33
+
34
+ <div style="text-align: left; margin: 20px 0;">
35
+ <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;">
36
+ Run them on the TensorBlock client using your local machine ↗
37
+ </a>
38
+ </div>
39
+
40
+ ## Prompt template
41
+
42
+ ```
43
+ <|im_start|>system
44
+ {system_prompt}<|im_end|>
45
+ <|im_start|>user
46
+ {prompt}<|im_end|>
47
+ <|im_start|>assistant
48
+ ```
49
+
50
+ ## Model file specification
51
+
52
+ | Filename | Quant type | File Size | Description |
53
+ | -------- | ---------- | --------- | ----------- |
54
+ | [Qwen2.5-32B-AGI-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-AGI-GGUF/blob/main/Qwen2.5-32B-AGI-Q2_K.gguf) | Q2_K | 12.313 GB | smallest, significant quality loss - not recommended for most purposes |
55
+ | [Qwen2.5-32B-AGI-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-AGI-GGUF/blob/main/Qwen2.5-32B-AGI-Q3_K_S.gguf) | Q3_K_S | 14.392 GB | very small, high quality loss |
56
+ | [Qwen2.5-32B-AGI-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-AGI-GGUF/blob/main/Qwen2.5-32B-AGI-Q3_K_M.gguf) | Q3_K_M | 15.935 GB | very small, high quality loss |
57
+ | [Qwen2.5-32B-AGI-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-AGI-GGUF/blob/main/Qwen2.5-32B-AGI-Q3_K_L.gguf) | Q3_K_L | 17.247 GB | small, substantial quality loss |
58
+ | [Qwen2.5-32B-AGI-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-AGI-GGUF/blob/main/Qwen2.5-32B-AGI-Q4_0.gguf) | Q4_0 | 18.640 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
59
+ | [Qwen2.5-32B-AGI-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-AGI-GGUF/blob/main/Qwen2.5-32B-AGI-Q4_K_S.gguf) | Q4_K_S | 18.784 GB | small, greater quality loss |
60
+ | [Qwen2.5-32B-AGI-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-AGI-GGUF/blob/main/Qwen2.5-32B-AGI-Q4_K_M.gguf) | Q4_K_M | 19.851 GB | medium, balanced quality - recommended |
61
+ | [Qwen2.5-32B-AGI-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-AGI-GGUF/blob/main/Qwen2.5-32B-AGI-Q5_0.gguf) | Q5_0 | 22.638 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
62
+ | [Qwen2.5-32B-AGI-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-AGI-GGUF/blob/main/Qwen2.5-32B-AGI-Q5_K_S.gguf) | Q5_K_S | 22.638 GB | large, low quality loss - recommended |
63
+ | [Qwen2.5-32B-AGI-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-AGI-GGUF/blob/main/Qwen2.5-32B-AGI-Q5_K_M.gguf) | Q5_K_M | 23.262 GB | large, very low quality loss - recommended |
64
+ | [Qwen2.5-32B-AGI-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-AGI-GGUF/blob/main/Qwen2.5-32B-AGI-Q6_K.gguf) | Q6_K | 26.886 GB | very large, extremely low quality loss |
65
+ | [Qwen2.5-32B-AGI-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen2.5-32B-AGI-GGUF/blob/main/Qwen2.5-32B-AGI-Q8_0.gguf) | Q8_0 | 34.821 GB | very large, extremely low quality loss - not recommended |
66
+
67
+
68
+ ## Downloading instruction
69
+
70
+ ### Command line
71
+
72
+ Firstly, install Huggingface Client
73
+
74
+ ```shell
75
+ pip install -U "huggingface_hub[cli]"
76
+ ```
77
+
78
+ Then, downoad the individual model file the a local directory
79
+
80
+ ```shell
81
+ huggingface-cli download tensorblock/Qwen2.5-32B-AGI-GGUF --include "Qwen2.5-32B-AGI-Q2_K.gguf" --local-dir MY_LOCAL_DIR
82
+ ```
83
+
84
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
85
+
86
+ ```shell
87
+ huggingface-cli download tensorblock/Qwen2.5-32B-AGI-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
88
+ ```