Hugging Face's logo

tensorblock
/
WiNGPT2-Llama-3-8B-Chat-GGUF

GGUF
English
Chinese
medical
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
458cb43
•
1 Parent(s): 31fa944

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +76 -0
  3. WiNGPT2-Llama-3-8B-Chat-Q2_K.gguf +3 -0
  4. WiNGPT2-Llama-3-8B-Chat-Q3_K_L.gguf +3 -0
  5. WiNGPT2-Llama-3-8B-Chat-Q3_K_M.gguf +3 -0
  6. WiNGPT2-Llama-3-8B-Chat-Q3_K_S.gguf +3 -0
  7. WiNGPT2-Llama-3-8B-Chat-Q4_0.gguf +3 -0
  8. WiNGPT2-Llama-3-8B-Chat-Q4_K_M.gguf +3 -0
  9. WiNGPT2-Llama-3-8B-Chat-Q4_K_S.gguf +3 -0
  10. WiNGPT2-Llama-3-8B-Chat-Q5_0.gguf +3 -0
  11. WiNGPT2-Llama-3-8B-Chat-Q5_K_M.gguf +3 -0
  12. WiNGPT2-Llama-3-8B-Chat-Q5_K_S.gguf +3 -0
  13. WiNGPT2-Llama-3-8B-Chat-Q6_K.gguf +3 -0
  14. WiNGPT2-Llama-3-8B-Chat-Q8_0.gguf +3 -0
.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
+ WiNGPT2-Llama-3-8B-Chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ WiNGPT2-Llama-3-8B-Chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ WiNGPT2-Llama-3-8B-Chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ WiNGPT2-Llama-3-8B-Chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ WiNGPT2-Llama-3-8B-Chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ WiNGPT2-Llama-3-8B-Chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ WiNGPT2-Llama-3-8B-Chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ WiNGPT2-Llama-3-8B-Chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ WiNGPT2-Llama-3-8B-Chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ WiNGPT2-Llama-3-8B-Chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ WiNGPT2-Llama-3-8B-Chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ WiNGPT2-Llama-3-8B-Chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ - zh
6
+ tags:
7
+ - medical
8
+ - TensorBlock
9
+ - GGUF
10
+ base_model: winninghealth/WiNGPT2-Llama-3-8B-Chat
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
+ ## winninghealth/WiNGPT2-Llama-3-8B-Chat - GGUF
25
+
26
+ This repo contains GGUF format model files for [winninghealth/WiNGPT2-Llama-3-8B-Chat](https://huggingface.co/winninghealth/WiNGPT2-Llama-3-8B-Chat).
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
+ System：{system_prompt}<|end_of_text|>
34
+ User：{prompt}<|end_of_text|>
35
+ Assistant：
36
+ ```
37
+
38
+ ## Model file specification
39
+
40
+ | Filename | Quant type | File Size | Description |
41
+ | -------- | ---------- | --------- | ----------- |
42
+ | [WiNGPT2-Llama-3-8B-Chat-Q2_K.gguf](https://huggingface.co/tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF/tree/main/WiNGPT2-Llama-3-8B-Chat-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
43
+ | [WiNGPT2-Llama-3-8B-Chat-Q3_K_S.gguf](https://huggingface.co/tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF/tree/main/WiNGPT2-Llama-3-8B-Chat-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
44
+ | [WiNGPT2-Llama-3-8B-Chat-Q3_K_M.gguf](https://huggingface.co/tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF/tree/main/WiNGPT2-Llama-3-8B-Chat-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
45
+ | [WiNGPT2-Llama-3-8B-Chat-Q3_K_L.gguf](https://huggingface.co/tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF/tree/main/WiNGPT2-Llama-3-8B-Chat-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
46
+ | [WiNGPT2-Llama-3-8B-Chat-Q4_0.gguf](https://huggingface.co/tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF/tree/main/WiNGPT2-Llama-3-8B-Chat-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
47
+ | [WiNGPT2-Llama-3-8B-Chat-Q4_K_S.gguf](https://huggingface.co/tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF/tree/main/WiNGPT2-Llama-3-8B-Chat-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
48
+ | [WiNGPT2-Llama-3-8B-Chat-Q4_K_M.gguf](https://huggingface.co/tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF/tree/main/WiNGPT2-Llama-3-8B-Chat-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
49
+ | [WiNGPT2-Llama-3-8B-Chat-Q5_0.gguf](https://huggingface.co/tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF/tree/main/WiNGPT2-Llama-3-8B-Chat-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
50
+ | [WiNGPT2-Llama-3-8B-Chat-Q5_K_S.gguf](https://huggingface.co/tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF/tree/main/WiNGPT2-Llama-3-8B-Chat-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
51
+ | [WiNGPT2-Llama-3-8B-Chat-Q5_K_M.gguf](https://huggingface.co/tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF/tree/main/WiNGPT2-Llama-3-8B-Chat-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
52
+ | [WiNGPT2-Llama-3-8B-Chat-Q6_K.gguf](https://huggingface.co/tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF/tree/main/WiNGPT2-Llama-3-8B-Chat-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
53
+ | [WiNGPT2-Llama-3-8B-Chat-Q8_0.gguf](https://huggingface.co/tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF/tree/main/WiNGPT2-Llama-3-8B-Chat-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
54
+
55
+
56
+ ## Downloading instruction
57
+
58
+ ### Command line
59
+
60
+ Firstly, install Huggingface Client
61
+
62
+ ```shell
63
+ pip install -U "huggingface_hub[cli]"
64
+ ```
65
+
66
+ Then, downoad the individual model file the a local directory
67
+
68
+ ```shell
69
+ huggingface-cli download tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF --include "WiNGPT2-Llama-3-8B-Chat-Q2_K.gguf" --local-dir MY_LOCAL_DIR
70
+ ```
71
+
72
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
73
+
74
+ ```shell
75
+ huggingface-cli download tensorblock/WiNGPT2-Llama-3-8B-Chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
76
+ ```
WiNGPT2-Llama-3-8B-Chat-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c71e29f82cfde94977737638ecca404b7495bda0e0f8712e0604d7ad6273014d
3
+ size 3179131424
WiNGPT2-Llama-3-8B-Chat-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f46013b84446af31197092e7ba116f7ea468d983addad1a0eb9578e3f8857a
3
+ size 4321956384
WiNGPT2-Llama-3-8B-Chat-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd1bc8e0df8f6e09a947ba27b7797fba5fb7119637746313fdec28dc483e5654
3
+ size 4018917920
WiNGPT2-Llama-3-8B-Chat-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea5e1eaa29ab9f68cbdb7159cc2cae896cf71ea288d8a427ae5285723f1c412
3
+ size 3664499232
WiNGPT2-Llama-3-8B-Chat-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc4b45982761964607a08d4a35bd1c20cb573cc5153cd18ca7b38d475b396a3
3
+ size 4661211680
WiNGPT2-Llama-3-8B-Chat-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a0a05bc4eef8742972a96ffe738aeacae87ce473f6c2c4307869802fba6aeae
3
+ size 4920734240
WiNGPT2-Llama-3-8B-Chat-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25dd1ac94762f62995cbc4d1ef5df1940a9a99b7eb8fb7cea698df9904a2d673
3
+ size 4692668960
WiNGPT2-Llama-3-8B-Chat-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99113ca15152ede0bb447e087ad1e1e3b07b8d42514003d4a9aa3bed723a6778
3
+ size 5599293984
WiNGPT2-Llama-3-8B-Chat-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d7592c310921508ec2f96af812281ce89fe5e1e6e1fac584c5557ea849fd11d
3
+ size 5732987424
WiNGPT2-Llama-3-8B-Chat-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d2949412ac6812cc7a23c13045b90864b14371c354b69469d996478bd717a69
3
+ size 5599293984
WiNGPT2-Llama-3-8B-Chat-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f443e774e26a38c7a629a4bb1ad763552c03f82b22af130cb57e6c5fc893c41
3
+ size 6596006432
WiNGPT2-Llama-3-8B-Chat-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f47d133dbe4291c14214cce8ba76b5320492b102de6c0e8264e2a9201ebabdd
3
+ size 8540770848