Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Llama-medx_v2-Q2_K.gguf +3 -0
- Llama-medx_v2-Q3_K_L.gguf +3 -0
- Llama-medx_v2-Q3_K_M.gguf +3 -0
- Llama-medx_v2-Q3_K_S.gguf +3 -0
- Llama-medx_v2-Q4_0.gguf +3 -0
- Llama-medx_v2-Q4_K_M.gguf +3 -0
- Llama-medx_v2-Q4_K_S.gguf +3 -0
- Llama-medx_v2-Q5_0.gguf +3 -0
- Llama-medx_v2-Q5_K_M.gguf +3 -0
- Llama-medx_v2-Q5_K_S.gguf +3 -0
- Llama-medx_v2-Q6_K.gguf +3 -0
- Llama-medx_v2-Q8_0.gguf +3 -0
- README.md +78 -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 |
+
Llama-medx_v2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Llama-medx_v2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Llama-medx_v2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Llama-medx_v2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Llama-medx_v2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Llama-medx_v2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Llama-medx_v2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Llama-medx_v2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Llama-medx_v2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Llama-medx_v2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Llama-medx_v2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Llama-medx_v2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Llama-medx_v2-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12f2d4f353d5b9246641cc8858d149aebd213e42bed95cff58a16c49f6fcc6a1
|
3 |
+
size 3179140736
|
Llama-medx_v2-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a78f9efc36e544557ac962bf2400dacb245d8ab8c53c2a73499946857ce0b80
|
3 |
+
size 4321966528
|
Llama-medx_v2-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eada8cf27c6caf2f573d1b76da623beda6e3873fbc86a0ade0bded6fe164bbd0
|
3 |
+
size 4018928064
|
Llama-medx_v2-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6312e0e77601cc70a73fa2066423cd979e95558a8b420f522207c1d5891cc7f3
|
3 |
+
size 3664509376
|
Llama-medx_v2-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce2bd7741092d4b5f52c04140ed3bf24b75578c88ae93660bf5fadb3faf76047
|
3 |
+
size 4661222912
|
Llama-medx_v2-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d902e340883998b938491fe0034952b3666581fb95150c3754f489528d56819
|
3 |
+
size 4920745472
|
Llama-medx_v2-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcf2c2046cdfb0876e32500938a69a035f95e85985ff7877202851d25a4c4b71
|
3 |
+
size 4692680192
|
Llama-medx_v2-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ef1dce203c1774ad86ca387d4cc293eec7c5db4313fa6066de53d7a51545651
|
3 |
+
size 5599306240
|
Llama-medx_v2-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d3bb5439b06b11bf8e92f1d8ece4fa7c7936bb30ca09e36228488caca3f57d6
|
3 |
+
size 5732999680
|
Llama-medx_v2-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9666769b1e9464e261ab3d5d493021bca200d81dbedb7ee131eac62626da013a
|
3 |
+
size 5599306240
|
Llama-medx_v2-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ee2ad899da8415ab63e88b6fb9c55bb615665ef352852376171d3d691831b62
|
3 |
+
size 6596019776
|
Llama-medx_v2-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed03e903cc11e32ca959454fce260a6817ac5fb19a3a0fd3224b12f09e713ede
|
3 |
+
size 8540788160
|
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
datasets:
|
5 |
+
- skumar9/orpo-mmlu
|
6 |
+
tags:
|
7 |
+
- medical
|
8 |
+
- TensorBlock
|
9 |
+
- GGUF
|
10 |
+
base_model: skumar9/Llama-medx_v2
|
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 |
+
## skumar9/Llama-medx_v2 - GGUF
|
25 |
+
|
26 |
+
This repo contains GGUF format model files for [skumar9/Llama-medx_v2](https://huggingface.co/skumar9/Llama-medx_v2).
|
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 |
+
<|im_start|>system
|
34 |
+
{system_prompt}<|im_end|>
|
35 |
+
<|im_start|>user
|
36 |
+
{prompt}<|im_end|>
|
37 |
+
<|im_start|>assistant
|
38 |
+
```
|
39 |
+
|
40 |
+
## Model file specification
|
41 |
+
|
42 |
+
| Filename | Quant type | File Size | Description |
|
43 |
+
| -------- | ---------- | --------- | ----------- |
|
44 |
+
| [Llama-medx_v2-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-medx_v2-GGUF/tree/main/Llama-medx_v2-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
|
45 |
+
| [Llama-medx_v2-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-medx_v2-GGUF/tree/main/Llama-medx_v2-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
|
46 |
+
| [Llama-medx_v2-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-medx_v2-GGUF/tree/main/Llama-medx_v2-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
|
47 |
+
| [Llama-medx_v2-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-medx_v2-GGUF/tree/main/Llama-medx_v2-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
|
48 |
+
| [Llama-medx_v2-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-medx_v2-GGUF/tree/main/Llama-medx_v2-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
49 |
+
| [Llama-medx_v2-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-medx_v2-GGUF/tree/main/Llama-medx_v2-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
|
50 |
+
| [Llama-medx_v2-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-medx_v2-GGUF/tree/main/Llama-medx_v2-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
|
51 |
+
| [Llama-medx_v2-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-medx_v2-GGUF/tree/main/Llama-medx_v2-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
52 |
+
| [Llama-medx_v2-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-medx_v2-GGUF/tree/main/Llama-medx_v2-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
|
53 |
+
| [Llama-medx_v2-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-medx_v2-GGUF/tree/main/Llama-medx_v2-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
|
54 |
+
| [Llama-medx_v2-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-medx_v2-GGUF/tree/main/Llama-medx_v2-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
|
55 |
+
| [Llama-medx_v2-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-medx_v2-GGUF/tree/main/Llama-medx_v2-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
|
56 |
+
|
57 |
+
|
58 |
+
## Downloading instruction
|
59 |
+
|
60 |
+
### Command line
|
61 |
+
|
62 |
+
Firstly, install Huggingface Client
|
63 |
+
|
64 |
+
```shell
|
65 |
+
pip install -U "huggingface_hub[cli]"
|
66 |
+
```
|
67 |
+
|
68 |
+
Then, downoad the individual model file the a local directory
|
69 |
+
|
70 |
+
```shell
|
71 |
+
huggingface-cli download tensorblock/Llama-medx_v2-GGUF --include "Llama-medx_v2-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
72 |
+
```
|
73 |
+
|
74 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
75 |
+
|
76 |
+
```shell
|
77 |
+
huggingface-cli download tensorblock/Llama-medx_v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
78 |
+
```
|