Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +74 -0
- medllama3-v20-Q2_K.gguf +3 -0
- medllama3-v20-Q3_K_L.gguf +3 -0
- medllama3-v20-Q3_K_M.gguf +3 -0
- medllama3-v20-Q3_K_S.gguf +3 -0
- medllama3-v20-Q4_0.gguf +3 -0
- medllama3-v20-Q4_K_M.gguf +3 -0
- medllama3-v20-Q4_K_S.gguf +3 -0
- medllama3-v20-Q5_0.gguf +3 -0
- medllama3-v20-Q5_K_M.gguf +3 -0
- medllama3-v20-Q5_K_S.gguf +3 -0
- medllama3-v20-Q6_K.gguf +3 -0
- medllama3-v20-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 |
+
medllama3-v20-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
medllama3-v20-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
medllama3-v20-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
medllama3-v20-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
medllama3-v20-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
medllama3-v20-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
medllama3-v20-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
medllama3-v20-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
medllama3-v20-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
medllama3-v20-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
medllama3-v20-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
medllama3-v20-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3
|
3 |
+
base_model: ProbeMedicalYonseiMAILab/medllama3-v20
|
4 |
+
tags:
|
5 |
+
- TensorBlock
|
6 |
+
- GGUF
|
7 |
+
---
|
8 |
+
|
9 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
10 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
11 |
+
</div>
|
12 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
13 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
14 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
15 |
+
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>
|
16 |
+
</p>
|
17 |
+
</div>
|
18 |
+
</div>
|
19 |
+
|
20 |
+
## ProbeMedicalYonseiMAILab/medllama3-v20 - GGUF
|
21 |
+
|
22 |
+
This repo contains GGUF format model files for [ProbeMedicalYonseiMAILab/medllama3-v20](https://huggingface.co/ProbeMedicalYonseiMAILab/medllama3-v20).
|
23 |
+
|
24 |
+
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).
|
25 |
+
|
26 |
+
## Prompt template
|
27 |
+
|
28 |
+
```
|
29 |
+
{system_prompt}
|
30 |
+
|
31 |
+
Human: {prompt}<|eot_id|>
|
32 |
+
|
33 |
+
Assistant:
|
34 |
+
```
|
35 |
+
|
36 |
+
## Model file specification
|
37 |
+
|
38 |
+
| Filename | Quant type | File Size | Description |
|
39 |
+
| -------- | ---------- | --------- | ----------- |
|
40 |
+
| [medllama3-v20-Q2_K.gguf](https://huggingface.co/tensorblock/medllama3-v20-GGUF/tree/main/medllama3-v20-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
|
41 |
+
| [medllama3-v20-Q3_K_S.gguf](https://huggingface.co/tensorblock/medllama3-v20-GGUF/tree/main/medllama3-v20-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
|
42 |
+
| [medllama3-v20-Q3_K_M.gguf](https://huggingface.co/tensorblock/medllama3-v20-GGUF/tree/main/medllama3-v20-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
|
43 |
+
| [medllama3-v20-Q3_K_L.gguf](https://huggingface.co/tensorblock/medllama3-v20-GGUF/tree/main/medllama3-v20-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
|
44 |
+
| [medllama3-v20-Q4_0.gguf](https://huggingface.co/tensorblock/medllama3-v20-GGUF/tree/main/medllama3-v20-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
45 |
+
| [medllama3-v20-Q4_K_S.gguf](https://huggingface.co/tensorblock/medllama3-v20-GGUF/tree/main/medllama3-v20-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
|
46 |
+
| [medllama3-v20-Q4_K_M.gguf](https://huggingface.co/tensorblock/medllama3-v20-GGUF/tree/main/medllama3-v20-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
|
47 |
+
| [medllama3-v20-Q5_0.gguf](https://huggingface.co/tensorblock/medllama3-v20-GGUF/tree/main/medllama3-v20-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
48 |
+
| [medllama3-v20-Q5_K_S.gguf](https://huggingface.co/tensorblock/medllama3-v20-GGUF/tree/main/medllama3-v20-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
|
49 |
+
| [medllama3-v20-Q5_K_M.gguf](https://huggingface.co/tensorblock/medllama3-v20-GGUF/tree/main/medllama3-v20-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
|
50 |
+
| [medllama3-v20-Q6_K.gguf](https://huggingface.co/tensorblock/medllama3-v20-GGUF/tree/main/medllama3-v20-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
|
51 |
+
| [medllama3-v20-Q8_0.gguf](https://huggingface.co/tensorblock/medllama3-v20-GGUF/tree/main/medllama3-v20-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
|
52 |
+
|
53 |
+
|
54 |
+
## Downloading instruction
|
55 |
+
|
56 |
+
### Command line
|
57 |
+
|
58 |
+
Firstly, install Huggingface Client
|
59 |
+
|
60 |
+
```shell
|
61 |
+
pip install -U "huggingface_hub[cli]"
|
62 |
+
```
|
63 |
+
|
64 |
+
Then, downoad the individual model file the a local directory
|
65 |
+
|
66 |
+
```shell
|
67 |
+
huggingface-cli download tensorblock/medllama3-v20-GGUF --include "medllama3-v20-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
68 |
+
```
|
69 |
+
|
70 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
71 |
+
|
72 |
+
```shell
|
73 |
+
huggingface-cli download tensorblock/medllama3-v20-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
74 |
+
```
|
medllama3-v20-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:423108a27d4db789976f1eb19db1b64dce180145c3d3a245433f85f8891ca3ad
|
3 |
+
size 3179131488
|
medllama3-v20-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa6ef8d168bc7be84355e8fded43a0b0a2af198931c874e201b0ff8a39629d63
|
3 |
+
size 4321956448
|
medllama3-v20-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:512d33f01a3aa886149cc1996be5d02ed9b33180a698948d518203e22fed4ab9
|
3 |
+
size 4018917984
|
medllama3-v20-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e58f8ac35ba97e4b50b92c9faf6b8b4a39983b0b5c22a4eb819031fc4022fce0
|
3 |
+
size 3664499296
|
medllama3-v20-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66961a743bddf307a8d535dd4a14ff2da45fe7540826a991fd6e62dccab2645f
|
3 |
+
size 4661211744
|
medllama3-v20-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a235a477cde36b4288adb032fc44f809cda8f96edfe590484d73555d7f0394af
|
3 |
+
size 4920734304
|
medllama3-v20-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fafe60f5f977041597cc66a66aa2e06aaecc8da0cb428ad986edfdd7a17dc4a7
|
3 |
+
size 4692669024
|
medllama3-v20-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b04bcd866a4749ed97620a482df81d0339784379fd7a1bc0e9dea50d0352c52
|
3 |
+
size 5599294048
|
medllama3-v20-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a53d10bf4362e13a4b38d98e87636f097d9626d7819415a297c3c04db730ab7
|
3 |
+
size 5732987488
|
medllama3-v20-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e165702c322d99075e34333b94fc1fb4edba6c8e57a4c80040ae0e9aa05ce817
|
3 |
+
size 5599294048
|
medllama3-v20-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85ab9783b92c36b7b6fc0a0c0a2b9dc26be45407321da4cf2fcd815da88a3b94
|
3 |
+
size 6596006496
|
medllama3-v20-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85fdb4d5396c771587e1134ca53c2ebc31e8049799de90a434eaef511b4deb2a
|
3 |
+
size 8540770912
|