Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- MedLlama-3-8B_DARE-Q2_K.gguf +3 -0
- MedLlama-3-8B_DARE-Q3_K_L.gguf +3 -0
- MedLlama-3-8B_DARE-Q3_K_M.gguf +3 -0
- MedLlama-3-8B_DARE-Q3_K_S.gguf +3 -0
- MedLlama-3-8B_DARE-Q4_0.gguf +3 -0
- MedLlama-3-8B_DARE-Q4_K_M.gguf +3 -0
- MedLlama-3-8B_DARE-Q4_K_S.gguf +3 -0
- MedLlama-3-8B_DARE-Q5_0.gguf +3 -0
- MedLlama-3-8B_DARE-Q5_K_M.gguf +3 -0
- MedLlama-3-8B_DARE-Q5_K_S.gguf +3 -0
- MedLlama-3-8B_DARE-Q6_K.gguf +3 -0
- MedLlama-3-8B_DARE-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 |
+
MedLlama-3-8B_DARE-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
MedLlama-3-8B_DARE-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
MedLlama-3-8B_DARE-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
MedLlama-3-8B_DARE-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
MedLlama-3-8B_DARE-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
MedLlama-3-8B_DARE-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
MedLlama-3-8B_DARE-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
MedLlama-3-8B_DARE-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
MedLlama-3-8B_DARE-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
MedLlama-3-8B_DARE-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
MedLlama-3-8B_DARE-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
MedLlama-3-8B_DARE-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
MedLlama-3-8B_DARE-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8715c8e9068088ae7964edc44ebe94a2d0cfa6d026c9c733ac2a4f0397e0773
|
3 |
+
size 3179131936
|
MedLlama-3-8B_DARE-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71d0fc51ac1d7c51477e612c9e5596df95e76bbe07160c23ab5d0da4576d3c43
|
3 |
+
size 4321956896
|
MedLlama-3-8B_DARE-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ce3b3cba7d1f20897ac86a0ab8f4755e382191c8177bd30a56074f63df38888
|
3 |
+
size 4018918432
|
MedLlama-3-8B_DARE-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:336762c3f79025dcb2de19503105c562f8e05fcd3704e7a1bfa230fa2a95ea11
|
3 |
+
size 3664499744
|
MedLlama-3-8B_DARE-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb81e9507a9e77507c908067aecaed9ea257f4f4358137dc3be10f29998edff4
|
3 |
+
size 4661212192
|
MedLlama-3-8B_DARE-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eded25427e231584778f5d595191794f7a929eb00f4a385c22f580c4b4b5c724
|
3 |
+
size 4920734752
|
MedLlama-3-8B_DARE-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf820660fd620f306ff904327bec4934584619764e45580ad222735e0d4381b4
|
3 |
+
size 4692669472
|
MedLlama-3-8B_DARE-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b50ccd2f833af1487f6a2835207469f2cdf9bccf955aa755c00ce3a7612216a9
|
3 |
+
size 5599294496
|
MedLlama-3-8B_DARE-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ef5068e11b59a29756addbc3c5d18b7b173783a48b8e11428f8eb2d92dfae62
|
3 |
+
size 5732987936
|
MedLlama-3-8B_DARE-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87d873e316fff5932e1c7104c534bc56b6a0fb3459c86c9defe3a8bcd1856514
|
3 |
+
size 5599294496
|
MedLlama-3-8B_DARE-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7167f42a15bbd9c0a5897064c98d21ef956836ed78cebffcb1f342fd04560c5d
|
3 |
+
size 6596006944
|
MedLlama-3-8B_DARE-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:562fa089a5e8d11f7a59073f91217850785958f08eb03c4f9c6d31cfbbc69d69
|
3 |
+
size 8540771360
|
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: ChenWeiLi/MedLlama-3-8B_DARE
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- mergekit
|
6 |
+
- merge
|
7 |
+
- TensorBlock
|
8 |
+
- GGUF
|
9 |
+
license: llama3
|
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 |
+
## ChenWeiLi/MedLlama-3-8B_DARE - GGUF
|
24 |
+
|
25 |
+
This repo contains GGUF format model files for [ChenWeiLi/MedLlama-3-8B_DARE](https://huggingface.co/ChenWeiLi/MedLlama-3-8B_DARE).
|
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 |
+
| [MedLlama-3-8B_DARE-Q2_K.gguf](https://huggingface.co/tensorblock/MedLlama-3-8B_DARE-GGUF/tree/main/MedLlama-3-8B_DARE-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
|
40 |
+
| [MedLlama-3-8B_DARE-Q3_K_S.gguf](https://huggingface.co/tensorblock/MedLlama-3-8B_DARE-GGUF/tree/main/MedLlama-3-8B_DARE-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
|
41 |
+
| [MedLlama-3-8B_DARE-Q3_K_M.gguf](https://huggingface.co/tensorblock/MedLlama-3-8B_DARE-GGUF/tree/main/MedLlama-3-8B_DARE-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
|
42 |
+
| [MedLlama-3-8B_DARE-Q3_K_L.gguf](https://huggingface.co/tensorblock/MedLlama-3-8B_DARE-GGUF/tree/main/MedLlama-3-8B_DARE-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
|
43 |
+
| [MedLlama-3-8B_DARE-Q4_0.gguf](https://huggingface.co/tensorblock/MedLlama-3-8B_DARE-GGUF/tree/main/MedLlama-3-8B_DARE-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
44 |
+
| [MedLlama-3-8B_DARE-Q4_K_S.gguf](https://huggingface.co/tensorblock/MedLlama-3-8B_DARE-GGUF/tree/main/MedLlama-3-8B_DARE-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
|
45 |
+
| [MedLlama-3-8B_DARE-Q4_K_M.gguf](https://huggingface.co/tensorblock/MedLlama-3-8B_DARE-GGUF/tree/main/MedLlama-3-8B_DARE-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
|
46 |
+
| [MedLlama-3-8B_DARE-Q5_0.gguf](https://huggingface.co/tensorblock/MedLlama-3-8B_DARE-GGUF/tree/main/MedLlama-3-8B_DARE-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
47 |
+
| [MedLlama-3-8B_DARE-Q5_K_S.gguf](https://huggingface.co/tensorblock/MedLlama-3-8B_DARE-GGUF/tree/main/MedLlama-3-8B_DARE-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
|
48 |
+
| [MedLlama-3-8B_DARE-Q5_K_M.gguf](https://huggingface.co/tensorblock/MedLlama-3-8B_DARE-GGUF/tree/main/MedLlama-3-8B_DARE-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
|
49 |
+
| [MedLlama-3-8B_DARE-Q6_K.gguf](https://huggingface.co/tensorblock/MedLlama-3-8B_DARE-GGUF/tree/main/MedLlama-3-8B_DARE-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
|
50 |
+
| [MedLlama-3-8B_DARE-Q8_0.gguf](https://huggingface.co/tensorblock/MedLlama-3-8B_DARE-GGUF/tree/main/MedLlama-3-8B_DARE-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/MedLlama-3-8B_DARE-GGUF --include "MedLlama-3-8B_DARE-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/MedLlama-3-8B_DARE-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
73 |
+
```
|