morriszms commited on
Commit
9cf8277
1 Parent(s): 42df79d

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
+ Qwen2-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Qwen2-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Qwen2-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Qwen2-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Qwen2-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Qwen2-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Qwen2-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Qwen2-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Qwen2-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Qwen2-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Qwen2-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Qwen2-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Qwen2-7B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a5981c6de2d187a9188eab0c1d516b6b9b3613215791626044b07522231e52
3
+ size 3015937856
Qwen2-7B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ffa85015e89a8f5490dee69f6cc78e60cd0bd08b36c752171ade1484c18433a
3
+ size 4088457024
Qwen2-7B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc60016a94e854a748868741901ccbd2b338ded4aa89626f98809c98c0393d8
3
+ size 3808388928
Qwen2-7B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee0da2991c837373d56d6a7abbdc8765e3338ebf7f30d3f8960bd388ff3daba
3
+ size 3492366144
Qwen2-7B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b48bab4842b14c58027d9816a392840c0932865c0c46b78222dbbdde82240ec9
3
+ size 4431388480
Qwen2-7B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f7cf3a665cc6ef6339d0fe63e5298f5e9af8d17df07b696e26ccaf81466f915
3
+ size 4683071296
Qwen2-7B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d438666b69735a898bc514b4be9b1134f2d6454ef721e2d22fd33706f34ef8e
3
+ size 4457766720
Qwen2-7B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a00062c5b74eba612c3264bb5ec0205cea27673321b6eb0e3a7f621952cc1d
3
+ size 5315174208
Qwen2-7B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a8da5c15721e7ac29c1b9a8775ac8bba2ef0d0f62b64ef44ee13c44852bde09
3
+ size 5444828992
Qwen2-7B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:631886e8f69d2f3145b641b5da686ee7dfb4d26390a2fdcdd95667377a3d0f2a
3
+ size 5315174208
Qwen2-7B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c76beb42010fe5a8e9ac442eb63c934b87d1e527accc0812138a070776eff74
3
+ size 6254196544
Qwen2-7B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31407d662e8863cf4c0c890a241ddc5117d40cd057b48a80146f3ed05014f38f
3
+ size 8098522944
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - pretrained
7
+ - TensorBlock
8
+ - GGUF
9
+ license: apache-2.0
10
+ base_model: Qwen/Qwen2-7B
11
+ ---
12
+
13
+ <div style="width: auto; margin-left: auto; margin-right: auto">
14
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
+ </div>
16
+ <div style="display: flex; justify-content: space-between; width: 100%;">
17
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
18
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
19
+ 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>
20
+ </p>
21
+ </div>
22
+ </div>
23
+
24
+ ## Qwen/Qwen2-7B - GGUF
25
+
26
+ This repo contains GGUF format model files for [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B).
27
+
28
+ 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).
29
+
30
+ ## Prompt template
31
+
32
+ ```
33
+ <|im_start|>system
34
+ {system_prompt}<|im_end|>
35
+ <|im_start|>user
36
+ {prompt}<|im_end|>
37
+ <|im_start|>assistant
38
+ ```
39
+
40
+ ## Model file specification
41
+
42
+ | Filename | Quant type | File Size | Description |
43
+ | -------- | ---------- | --------- | ----------- |
44
+ | [Qwen2-7B-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q2_K.gguf) | Q2_K | 2.809 GB | smallest, significant quality loss - not recommended for most purposes |
45
+ | [Qwen2-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q3_K_S.gguf) | Q3_K_S | 3.253 GB | very small, high quality loss |
46
+ | [Qwen2-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q3_K_M.gguf) | Q3_K_M | 3.547 GB | very small, high quality loss |
47
+ | [Qwen2-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q3_K_L.gguf) | Q3_K_L | 3.808 GB | small, substantial quality loss |
48
+ | [Qwen2-7B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q4_0.gguf) | Q4_0 | 4.127 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
49
+ | [Qwen2-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q4_K_S.gguf) | Q4_K_S | 4.152 GB | small, greater quality loss |
50
+ | [Qwen2-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q4_K_M.gguf) | Q4_K_M | 4.361 GB | medium, balanced quality - recommended |
51
+ | [Qwen2-7B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q5_0.gguf) | Q5_0 | 4.950 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
52
+ | [Qwen2-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q5_K_S.gguf) | Q5_K_S | 4.950 GB | large, low quality loss - recommended |
53
+ | [Qwen2-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q5_K_M.gguf) | Q5_K_M | 5.071 GB | large, very low quality loss - recommended |
54
+ | [Qwen2-7B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q6_K.gguf) | Q6_K | 5.825 GB | very large, extremely low quality loss |
55
+ | [Qwen2-7B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen2-7B-GGUF/tree/main/Qwen2-7B-Q8_0.gguf) | Q8_0 | 7.542 GB | very large, extremely low quality loss - not recommended |
56
+
57
+
58
+ ## Downloading instruction
59
+
60
+ ### Command line
61
+
62
+ Firstly, install Huggingface Client
63
+
64
+ ```shell
65
+ pip install -U "huggingface_hub[cli]"
66
+ ```
67
+
68
+ Then, downoad the individual model file the a local directory
69
+
70
+ ```shell
71
+ huggingface-cli download tensorblock/Qwen2-7B-GGUF --include "Qwen2-7B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
72
+ ```
73
+
74
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
75
+
76
+ ```shell
77
+ huggingface-cli download tensorblock/Qwen2-7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
78
+ ```