Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- JSL-MedMNX-7B-SFT-Q2_K.gguf +3 -0
- JSL-MedMNX-7B-SFT-Q3_K_L.gguf +3 -0
- JSL-MedMNX-7B-SFT-Q3_K_M.gguf +3 -0
- JSL-MedMNX-7B-SFT-Q3_K_S.gguf +3 -0
- JSL-MedMNX-7B-SFT-Q4_0.gguf +3 -0
- JSL-MedMNX-7B-SFT-Q4_K_M.gguf +3 -0
- JSL-MedMNX-7B-SFT-Q4_K_S.gguf +3 -0
- JSL-MedMNX-7B-SFT-Q5_0.gguf +3 -0
- JSL-MedMNX-7B-SFT-Q5_K_M.gguf +3 -0
- JSL-MedMNX-7B-SFT-Q5_K_S.gguf +3 -0
- JSL-MedMNX-7B-SFT-Q6_K.gguf +3 -0
- JSL-MedMNX-7B-SFT-Q8_0.gguf +3 -0
- README.md +76 -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 |
+
JSL-MedMNX-7B-SFT-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
JSL-MedMNX-7B-SFT-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
JSL-MedMNX-7B-SFT-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
JSL-MedMNX-7B-SFT-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
JSL-MedMNX-7B-SFT-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
JSL-MedMNX-7B-SFT-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
JSL-MedMNX-7B-SFT-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
JSL-MedMNX-7B-SFT-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
JSL-MedMNX-7B-SFT-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
JSL-MedMNX-7B-SFT-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
JSL-MedMNX-7B-SFT-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
JSL-MedMNX-7B-SFT-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
JSL-MedMNX-7B-SFT-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4897475bf363629e03561dca578774e61be12ddb4ff7cfb77a32e54f3855197
|
3 |
+
size 2719252192
|
JSL-MedMNX-7B-SFT-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3be5185aa9bf37089bcdae6e38d96827d6e03f4d9170967ad539176f1d5e4015
|
3 |
+
size 3822035488
|
JSL-MedMNX-7B-SFT-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2604d8dba18775cc5dda42a8a2ae35a799cb78c8300a1961c44f07bf075e3a21
|
3 |
+
size 3518997024
|
JSL-MedMNX-7B-SFT-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db6aa703d6f41d63e52de5200b98df2462cb5d761215a115fd90340c655536a6
|
3 |
+
size 3164578336
|
JSL-MedMNX-7B-SFT-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48478ef76a9e1e5ad3729da676f79499aac7a623bb6a510a11a906d31e259760
|
3 |
+
size 4108928608
|
JSL-MedMNX-7B-SFT-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c138826aab999c325735e1be2f9c5d1098deb53aeda59c70100aba098a9e650c
|
3 |
+
size 4368451168
|
JSL-MedMNX-7B-SFT-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd9ba4bfebc69287614a094fdea868ae402afd14d076fac2c46db8a07fb42af2
|
3 |
+
size 4140385888
|
JSL-MedMNX-7B-SFT-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bacfde31b10d512584481817f40caf3b327f2d5a5f7bed45a6a7a1fcc1f8d36c
|
3 |
+
size 4997728864
|
JSL-MedMNX-7B-SFT-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cc34a1f8794c3284979c9ff2dfd505de005d9ce35cbb208fbd2c2ab7c236242
|
3 |
+
size 5131422304
|
JSL-MedMNX-7B-SFT-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d560b2b81e0d64becd710b2cb2487c12e67979f0a997fa37ded162d0556fa5f1
|
3 |
+
size 4997728864
|
JSL-MedMNX-7B-SFT-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47d5b74d22d4390064460b29fd2fb87cbb981fc69ebdc12ffa0c8153bc237e43
|
3 |
+
size 5942079136
|
JSL-MedMNX-7B-SFT-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07b5067b6cc3b5b05711e135b7bd099f217d0d2a4958b4d51b2a1cbe7a3e9dc5
|
3 |
+
size 7695875616
|
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-nd-4.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- reward model
|
8 |
+
- RLHF
|
9 |
+
- medical
|
10 |
+
- TensorBlock
|
11 |
+
- GGUF
|
12 |
+
base_model: johnsnowlabs/JSL-MedMNX-7B-SFT
|
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 |
+
## johnsnowlabs/JSL-MedMNX-7B-SFT - GGUF
|
27 |
+
|
28 |
+
This repo contains GGUF format model files for [johnsnowlabs/JSL-MedMNX-7B-SFT](https://huggingface.co/johnsnowlabs/JSL-MedMNX-7B-SFT).
|
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 |
+
<s>GPT4 Correct System: {system_prompt}<|end_of_turn|>GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:
|
36 |
+
```
|
37 |
+
|
38 |
+
## Model file specification
|
39 |
+
|
40 |
+
| Filename | Quant type | File Size | Description |
|
41 |
+
| -------- | ---------- | --------- | ----------- |
|
42 |
+
| [JSL-MedMNX-7B-SFT-Q2_K.gguf](https://huggingface.co/tensorblock/JSL-MedMNX-7B-SFT-GGUF/tree/main/JSL-MedMNX-7B-SFT-Q2_K.gguf) | Q2_K | 2.533 GB | smallest, significant quality loss - not recommended for most purposes |
|
43 |
+
| [JSL-MedMNX-7B-SFT-Q3_K_S.gguf](https://huggingface.co/tensorblock/JSL-MedMNX-7B-SFT-GGUF/tree/main/JSL-MedMNX-7B-SFT-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
|
44 |
+
| [JSL-MedMNX-7B-SFT-Q3_K_M.gguf](https://huggingface.co/tensorblock/JSL-MedMNX-7B-SFT-GGUF/tree/main/JSL-MedMNX-7B-SFT-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
|
45 |
+
| [JSL-MedMNX-7B-SFT-Q3_K_L.gguf](https://huggingface.co/tensorblock/JSL-MedMNX-7B-SFT-GGUF/tree/main/JSL-MedMNX-7B-SFT-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
|
46 |
+
| [JSL-MedMNX-7B-SFT-Q4_0.gguf](https://huggingface.co/tensorblock/JSL-MedMNX-7B-SFT-GGUF/tree/main/JSL-MedMNX-7B-SFT-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
47 |
+
| [JSL-MedMNX-7B-SFT-Q4_K_S.gguf](https://huggingface.co/tensorblock/JSL-MedMNX-7B-SFT-GGUF/tree/main/JSL-MedMNX-7B-SFT-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
|
48 |
+
| [JSL-MedMNX-7B-SFT-Q4_K_M.gguf](https://huggingface.co/tensorblock/JSL-MedMNX-7B-SFT-GGUF/tree/main/JSL-MedMNX-7B-SFT-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
|
49 |
+
| [JSL-MedMNX-7B-SFT-Q5_0.gguf](https://huggingface.co/tensorblock/JSL-MedMNX-7B-SFT-GGUF/tree/main/JSL-MedMNX-7B-SFT-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
50 |
+
| [JSL-MedMNX-7B-SFT-Q5_K_S.gguf](https://huggingface.co/tensorblock/JSL-MedMNX-7B-SFT-GGUF/tree/main/JSL-MedMNX-7B-SFT-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
|
51 |
+
| [JSL-MedMNX-7B-SFT-Q5_K_M.gguf](https://huggingface.co/tensorblock/JSL-MedMNX-7B-SFT-GGUF/tree/main/JSL-MedMNX-7B-SFT-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
|
52 |
+
| [JSL-MedMNX-7B-SFT-Q6_K.gguf](https://huggingface.co/tensorblock/JSL-MedMNX-7B-SFT-GGUF/tree/main/JSL-MedMNX-7B-SFT-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
|
53 |
+
| [JSL-MedMNX-7B-SFT-Q8_0.gguf](https://huggingface.co/tensorblock/JSL-MedMNX-7B-SFT-GGUF/tree/main/JSL-MedMNX-7B-SFT-Q8_0.gguf) | Q8_0 | 7.167 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/JSL-MedMNX-7B-SFT-GGUF --include "JSL-MedMNX-7B-SFT-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/JSL-MedMNX-7B-SFT-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
76 |
+
```
|