morriszms commited on
Commit
ef1d9d0
·
verified ·
1 Parent(s): a43dac5

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
+ Pretrain-Qwen-200M-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Pretrain-Qwen-200M-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Pretrain-Qwen-200M-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Pretrain-Qwen-200M-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Pretrain-Qwen-200M-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Pretrain-Qwen-200M-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Pretrain-Qwen-200M-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Pretrain-Qwen-200M-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Pretrain-Qwen-200M-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Pretrain-Qwen-200M-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Pretrain-Qwen-200M-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Pretrain-Qwen-200M-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Pretrain-Qwen-200M-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0618b9a522800d9ffecd3652690178704322df2a78f368069ef651a7cdd6802
3
+ size 136294240
Pretrain-Qwen-200M-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb0f177371a81b02a58f613b8d72f18a8445fb02670dbccb6792ee02800511b8
3
+ size 148984672
Pretrain-Qwen-200M-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5a52725dfe99fc3d349d05a1e077d552d5df93a0061ad7820a805532e1c7eab
3
+ size 146146144
Pretrain-Qwen-200M-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abcf602488efd2047f3e7c31e84a5f8f687b5f8e7cb94c10827fd3adc72bb7d1
3
+ size 141685600
Pretrain-Qwen-200M-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6651f81357d636b9959e6da33d9921801cc96f8407b699d8a0427072b45f61c2
3
+ size 150615904
Pretrain-Qwen-200M-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c59e9324adc28dc96f6e68a385f4b049e0aca112575f2e221d0cab7936628b8
3
+ size 157610848
Pretrain-Qwen-200M-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:161699bd76740bb8a405ce270ad1a1484c36339975762924481baa63ca7e20a5
3
+ size 153445216
Pretrain-Qwen-200M-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:888cc88c7b3ee80ef23204bc9c6985b7edae3420edfa04d9492af8827270543e
3
+ size 161453920
Pretrain-Qwen-200M-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f977163305560b0e9f5901d5c933fbd236076ad48d44e9cb4c6e93cc5927d981
3
+ size 166181728
Pretrain-Qwen-200M-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5f2edb27786ef4f47fce0092dfb7ff706a1d7424230d3f75bdc618b72910bc
3
+ size 162670432
Pretrain-Qwen-200M-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d0418094f59363de0b3c10298eb2a89a21494f2b33c21d822d437b5e8e493e3
3
+ size 177683296
Pretrain-Qwen-200M-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b9732d3ab9fe2a914c88a446600ad9dbb7df3ca97c61bb8ace69a2e07bac847
3
+ size 222228064
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ datasets:
5
+ - monology/pile-uncopyrighted
6
+ - MiniLLM/pile-tokenized
7
+ language:
8
+ - en
9
+ metrics:
10
+ - accuracy
11
+ pipeline_tag: text-generation
12
+ tags:
13
+ - TensorBlock
14
+ - GGUF
15
+ base_model: MiniLLM/Pretrain-Qwen-200M
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
+ ## MiniLLM/Pretrain-Qwen-200M - GGUF
30
+
31
+ This repo contains GGUF format model files for [MiniLLM/Pretrain-Qwen-200M](https://huggingface.co/MiniLLM/Pretrain-Qwen-200M).
32
+
33
+ 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).
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
+ | [Pretrain-Qwen-200M-Q2_K.gguf](https://huggingface.co/tensorblock/Pretrain-Qwen-200M-GGUF/blob/main/Pretrain-Qwen-200M-Q2_K.gguf) | Q2_K | 0.136 GB | smallest, significant quality loss - not recommended for most purposes |
56
+ | [Pretrain-Qwen-200M-Q3_K_S.gguf](https://huggingface.co/tensorblock/Pretrain-Qwen-200M-GGUF/blob/main/Pretrain-Qwen-200M-Q3_K_S.gguf) | Q3_K_S | 0.142 GB | very small, high quality loss |
57
+ | [Pretrain-Qwen-200M-Q3_K_M.gguf](https://huggingface.co/tensorblock/Pretrain-Qwen-200M-GGUF/blob/main/Pretrain-Qwen-200M-Q3_K_M.gguf) | Q3_K_M | 0.146 GB | very small, high quality loss |
58
+ | [Pretrain-Qwen-200M-Q3_K_L.gguf](https://huggingface.co/tensorblock/Pretrain-Qwen-200M-GGUF/blob/main/Pretrain-Qwen-200M-Q3_K_L.gguf) | Q3_K_L | 0.149 GB | small, substantial quality loss |
59
+ | [Pretrain-Qwen-200M-Q4_0.gguf](https://huggingface.co/tensorblock/Pretrain-Qwen-200M-GGUF/blob/main/Pretrain-Qwen-200M-Q4_0.gguf) | Q4_0 | 0.151 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
60
+ | [Pretrain-Qwen-200M-Q4_K_S.gguf](https://huggingface.co/tensorblock/Pretrain-Qwen-200M-GGUF/blob/main/Pretrain-Qwen-200M-Q4_K_S.gguf) | Q4_K_S | 0.153 GB | small, greater quality loss |
61
+ | [Pretrain-Qwen-200M-Q4_K_M.gguf](https://huggingface.co/tensorblock/Pretrain-Qwen-200M-GGUF/blob/main/Pretrain-Qwen-200M-Q4_K_M.gguf) | Q4_K_M | 0.158 GB | medium, balanced quality - recommended |
62
+ | [Pretrain-Qwen-200M-Q5_0.gguf](https://huggingface.co/tensorblock/Pretrain-Qwen-200M-GGUF/blob/main/Pretrain-Qwen-200M-Q5_0.gguf) | Q5_0 | 0.161 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
63
+ | [Pretrain-Qwen-200M-Q5_K_S.gguf](https://huggingface.co/tensorblock/Pretrain-Qwen-200M-GGUF/blob/main/Pretrain-Qwen-200M-Q5_K_S.gguf) | Q5_K_S | 0.163 GB | large, low quality loss - recommended |
64
+ | [Pretrain-Qwen-200M-Q5_K_M.gguf](https://huggingface.co/tensorblock/Pretrain-Qwen-200M-GGUF/blob/main/Pretrain-Qwen-200M-Q5_K_M.gguf) | Q5_K_M | 0.166 GB | large, very low quality loss - recommended |
65
+ | [Pretrain-Qwen-200M-Q6_K.gguf](https://huggingface.co/tensorblock/Pretrain-Qwen-200M-GGUF/blob/main/Pretrain-Qwen-200M-Q6_K.gguf) | Q6_K | 0.178 GB | very large, extremely low quality loss |
66
+ | [Pretrain-Qwen-200M-Q8_0.gguf](https://huggingface.co/tensorblock/Pretrain-Qwen-200M-GGUF/blob/main/Pretrain-Qwen-200M-Q8_0.gguf) | Q8_0 | 0.222 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/Pretrain-Qwen-200M-GGUF --include "Pretrain-Qwen-200M-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/Pretrain-Qwen-200M-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
89
+ ```