Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- JSL-Med-Sft-Llama-3-8B-Q2_K.gguf +3 -0
- JSL-Med-Sft-Llama-3-8B-Q3_K_L.gguf +3 -0
- JSL-Med-Sft-Llama-3-8B-Q3_K_M.gguf +3 -0
- JSL-Med-Sft-Llama-3-8B-Q3_K_S.gguf +3 -0
- JSL-Med-Sft-Llama-3-8B-Q4_0.gguf +3 -0
- JSL-Med-Sft-Llama-3-8B-Q4_K_M.gguf +3 -0
- JSL-Med-Sft-Llama-3-8B-Q4_K_S.gguf +3 -0
- JSL-Med-Sft-Llama-3-8B-Q5_0.gguf +3 -0
- JSL-Med-Sft-Llama-3-8B-Q5_K_M.gguf +3 -0
- JSL-Med-Sft-Llama-3-8B-Q5_K_S.gguf +3 -0
- JSL-Med-Sft-Llama-3-8B-Q6_K.gguf +3 -0
- JSL-Med-Sft-Llama-3-8B-Q8_0.gguf +3 -0
- README.md +73 -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-Med-Sft-Llama-3-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
JSL-Med-Sft-Llama-3-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
JSL-Med-Sft-Llama-3-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
JSL-Med-Sft-Llama-3-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
JSL-Med-Sft-Llama-3-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
JSL-Med-Sft-Llama-3-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
JSL-Med-Sft-Llama-3-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
JSL-Med-Sft-Llama-3-8B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
JSL-Med-Sft-Llama-3-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
JSL-Med-Sft-Llama-3-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
JSL-Med-Sft-Llama-3-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
JSL-Med-Sft-Llama-3-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
JSL-Med-Sft-Llama-3-8B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52433f3e835152f4f111ac1e679a3f3069c6add544e49b1034a3cab7686f9310
|
3 |
+
size 3179131296
|
JSL-Med-Sft-Llama-3-8B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea4681b6082470e08a7d184e813ff992a564f83776c85c025fdb5a9f5e07ff21
|
3 |
+
size 4321956256
|
JSL-Med-Sft-Llama-3-8B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:739935c9f23b86769cf2ce76515ce85652948167de494beab710faa6f4b3489a
|
3 |
+
size 4018917792
|
JSL-Med-Sft-Llama-3-8B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8516febac54cb81c5786e576d64bdf28969f3deb6aa3cf26babd081f4430fbed
|
3 |
+
size 3664499104
|
JSL-Med-Sft-Llama-3-8B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef9edf74a959e87ec98980a699c85c93fa7df7288e72715d63017517fc0b973e
|
3 |
+
size 4661211552
|
JSL-Med-Sft-Llama-3-8B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a248a79f064a2138def19c01ad1b9de80f5746cbb1684cb3b8139182a6a39a06
|
3 |
+
size 4920734112
|
JSL-Med-Sft-Llama-3-8B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a787ef91a60f7bb2e2d46d25e224958a1f50f8ba403fac680149c36c1e8ef28
|
3 |
+
size 4692668832
|
JSL-Med-Sft-Llama-3-8B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e06a54ee1404b73707243aee89876d8780161328a0214f3de8086bfd646c468d
|
3 |
+
size 5599293856
|
JSL-Med-Sft-Llama-3-8B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f79df813ccb72b47ed14d8ce80926ca36250ebc60eb0b07d7621a8dca1465d3
|
3 |
+
size 5732987296
|
JSL-Med-Sft-Llama-3-8B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa5847deabfc9235aeb54eb3646ac8ddab4e0edc54248260279df73d33343b75
|
3 |
+
size 5599293856
|
JSL-Med-Sft-Llama-3-8B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0435208d1ee309f41e2eba29ed9075ee19781aa7693b9f684f33b3394a371691
|
3 |
+
size 6596006304
|
JSL-Med-Sft-Llama-3-8B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f313f2944be5099bc827752d654afa77de102ffd63c4c0d5b7436d90f9523cf
|
3 |
+
size 8540770720
|
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- llama-3-8b
|
4 |
+
- sft
|
5 |
+
- medical
|
6 |
+
- TensorBlock
|
7 |
+
- GGUF
|
8 |
+
base_model: johnsnowlabs/JSL-Med-Sft-Llama-3-8B
|
9 |
+
license: cc-by-nc-nd-4.0
|
10 |
+
---
|
11 |
+
|
12 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
13 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
14 |
+
</div>
|
15 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
16 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
17 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
18 |
+
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>
|
19 |
+
</p>
|
20 |
+
</div>
|
21 |
+
</div>
|
22 |
+
|
23 |
+
## johnsnowlabs/JSL-Med-Sft-Llama-3-8B - GGUF
|
24 |
+
|
25 |
+
This repo contains GGUF format model files for [johnsnowlabs/JSL-Med-Sft-Llama-3-8B](https://huggingface.co/johnsnowlabs/JSL-Med-Sft-Llama-3-8B).
|
26 |
+
|
27 |
+
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).
|
28 |
+
|
29 |
+
## Prompt template
|
30 |
+
|
31 |
+
```
|
32 |
+
|
33 |
+
```
|
34 |
+
|
35 |
+
## Model file specification
|
36 |
+
|
37 |
+
| Filename | Quant type | File Size | Description |
|
38 |
+
| -------- | ---------- | --------- | ----------- |
|
39 |
+
| [JSL-Med-Sft-Llama-3-8B-Q2_K.gguf](https://huggingface.co/tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF/tree/main/JSL-Med-Sft-Llama-3-8B-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
|
40 |
+
| [JSL-Med-Sft-Llama-3-8B-Q3_K_S.gguf](https://huggingface.co/tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF/tree/main/JSL-Med-Sft-Llama-3-8B-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
|
41 |
+
| [JSL-Med-Sft-Llama-3-8B-Q3_K_M.gguf](https://huggingface.co/tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF/tree/main/JSL-Med-Sft-Llama-3-8B-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
|
42 |
+
| [JSL-Med-Sft-Llama-3-8B-Q3_K_L.gguf](https://huggingface.co/tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF/tree/main/JSL-Med-Sft-Llama-3-8B-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
|
43 |
+
| [JSL-Med-Sft-Llama-3-8B-Q4_0.gguf](https://huggingface.co/tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF/tree/main/JSL-Med-Sft-Llama-3-8B-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
44 |
+
| [JSL-Med-Sft-Llama-3-8B-Q4_K_S.gguf](https://huggingface.co/tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF/tree/main/JSL-Med-Sft-Llama-3-8B-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
|
45 |
+
| [JSL-Med-Sft-Llama-3-8B-Q4_K_M.gguf](https://huggingface.co/tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF/tree/main/JSL-Med-Sft-Llama-3-8B-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
|
46 |
+
| [JSL-Med-Sft-Llama-3-8B-Q5_0.gguf](https://huggingface.co/tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF/tree/main/JSL-Med-Sft-Llama-3-8B-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
47 |
+
| [JSL-Med-Sft-Llama-3-8B-Q5_K_S.gguf](https://huggingface.co/tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF/tree/main/JSL-Med-Sft-Llama-3-8B-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
|
48 |
+
| [JSL-Med-Sft-Llama-3-8B-Q5_K_M.gguf](https://huggingface.co/tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF/tree/main/JSL-Med-Sft-Llama-3-8B-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
|
49 |
+
| [JSL-Med-Sft-Llama-3-8B-Q6_K.gguf](https://huggingface.co/tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF/tree/main/JSL-Med-Sft-Llama-3-8B-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
|
50 |
+
| [JSL-Med-Sft-Llama-3-8B-Q8_0.gguf](https://huggingface.co/tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF/tree/main/JSL-Med-Sft-Llama-3-8B-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
|
51 |
+
|
52 |
+
|
53 |
+
## Downloading instruction
|
54 |
+
|
55 |
+
### Command line
|
56 |
+
|
57 |
+
Firstly, install Huggingface Client
|
58 |
+
|
59 |
+
```shell
|
60 |
+
pip install -U "huggingface_hub[cli]"
|
61 |
+
```
|
62 |
+
|
63 |
+
Then, downoad the individual model file the a local directory
|
64 |
+
|
65 |
+
```shell
|
66 |
+
huggingface-cli download tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF --include "JSL-Med-Sft-Llama-3-8B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
67 |
+
```
|
68 |
+
|
69 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
70 |
+
|
71 |
+
```shell
|
72 |
+
huggingface-cli download tensorblock/JSL-Med-Sft-Llama-3-8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
73 |
+
```
|