Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Qwen3_Medical_GRPO-Q2_K.gguf +3 -0
- Qwen3_Medical_GRPO-Q3_K_L.gguf +3 -0
- Qwen3_Medical_GRPO-Q3_K_M.gguf +3 -0
- Qwen3_Medical_GRPO-Q3_K_S.gguf +3 -0
- Qwen3_Medical_GRPO-Q4_0.gguf +3 -0
- Qwen3_Medical_GRPO-Q4_K_M.gguf +3 -0
- Qwen3_Medical_GRPO-Q4_K_S.gguf +3 -0
- Qwen3_Medical_GRPO-Q5_0.gguf +3 -0
- Qwen3_Medical_GRPO-Q5_K_M.gguf +3 -0
- Qwen3_Medical_GRPO-Q5_K_S.gguf +3 -0
- Qwen3_Medical_GRPO-Q6_K.gguf +3 -0
- Qwen3_Medical_GRPO-Q8_0.gguf +3 -0
- README.md +156 -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 |
+
Qwen3_Medical_GRPO-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Qwen3_Medical_GRPO-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Qwen3_Medical_GRPO-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Qwen3_Medical_GRPO-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Qwen3_Medical_GRPO-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Qwen3_Medical_GRPO-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Qwen3_Medical_GRPO-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Qwen3_Medical_GRPO-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Qwen3_Medical_GRPO-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Qwen3_Medical_GRPO-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Qwen3_Medical_GRPO-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Qwen3_Medical_GRPO-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Qwen3_Medical_GRPO-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb7e84dc16f35d376f296847ff852a8f18ff7a7b3ef26f12f90635e4f842288c
|
3 |
+
size 1669495904
|
Qwen3_Medical_GRPO-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c31dc398e7f7c961238d653cb0996fdaa7544d1b7660048116d16556efdea2d
|
3 |
+
size 2239781984
|
Qwen3_Medical_GRPO-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4b905bfc5f66dcfe6eef08fb4429123822fe76af939addd4f5a8fa66326823c
|
3 |
+
size 2075614304
|
Qwen3_Medical_GRPO-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a875f53836e4f3ffb467d7c5c058875c41e66f3a2ab03db56ec2fa774e251633
|
3 |
+
size 1886993504
|
Qwen3_Medical_GRPO-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2d8c3b221a04b938878b09fffaa3b9c9fb82290faef59447b8717f2480b8471
|
3 |
+
size 2369543264
|
Qwen3_Medical_GRPO-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97172518e7d4568b3c9236afa60aa61656eb2d7a9542930501deda2e74fef3ae
|
3 |
+
size 2497277024
|
Qwen3_Medical_GRPO-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b4b088b09f3ab0d08edef1bc7cb4ad1130ebdf6ee204dc0a225dccb857d6ca3
|
3 |
+
size 2383305824
|
Qwen3_Medical_GRPO-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4ae1c756a0ddefb66a28a32f87b650f82b14bcf8fd4907d2442f4d39bc2fda4
|
3 |
+
size 2823707744
|
Qwen3_Medical_GRPO-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8c1bba5bb237ee209f57f40f2bc2420470294d07e54cd97929466a61d834ce0
|
3 |
+
size 2889509984
|
Qwen3_Medical_GRPO-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:305f0326142a864c65bfb08f7b066c507746de2c86259a85989bf5f3d3375198
|
3 |
+
size 2823707744
|
Qwen3_Medical_GRPO-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96c88fbb1285b85c876474c0a2dac95207abbd52412d837b30d620a1339bff5a
|
3 |
+
size 3306257504
|
Qwen3_Medical_GRPO-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa428f2a32c156978fb38afce3f06c5b897af9baac91819a880e3913d3c92e98
|
3 |
+
size 4280401504
|
README.md
ADDED
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: lastmass/Qwen3_Medical_GRPO
|
3 |
+
tags:
|
4 |
+
- text-generation-inference
|
5 |
+
- transformers
|
6 |
+
- unsloth
|
7 |
+
- qwen3
|
8 |
+
- vllm
|
9 |
+
- medical
|
10 |
+
- TensorBlock
|
11 |
+
- GGUF
|
12 |
+
license: apache-2.0
|
13 |
+
language:
|
14 |
+
- en
|
15 |
+
- zh
|
16 |
+
datasets:
|
17 |
+
- FreedomIntelligence/medical-o1-reasoning-SFT
|
18 |
+
- lastmass/medical-o1-reasoning-SFT-keywords
|
19 |
+
---
|
20 |
+
|
21 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
22 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
23 |
+
</div>
|
24 |
+
|
25 |
+
[](https://tensorblock.co)
|
26 |
+
[](https://twitter.com/tensorblock_aoi)
|
27 |
+
[](https://discord.gg/Ej5NmeHFf2)
|
28 |
+
[](https://github.com/TensorBlock)
|
29 |
+
[](https://t.me/TensorBlock)
|
30 |
+
|
31 |
+
|
32 |
+
## lastmass/Qwen3_Medical_GRPO - GGUF
|
33 |
+
|
34 |
+
<div style="text-align: left; margin: 20px 0;">
|
35 |
+
<a href="https://discord.com/invite/Ej5NmeHFf2" style="display: inline-block; padding: 10px 20px; background-color: #5865F2; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
|
36 |
+
Join our Discord to learn more about what we're building β
|
37 |
+
</a>
|
38 |
+
</div>
|
39 |
+
|
40 |
+
This repo contains GGUF format model files for [lastmass/Qwen3_Medical_GRPO](https://huggingface.co/lastmass/Qwen3_Medical_GRPO).
|
41 |
+
|
42 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5753](https://github.com/ggml-org/llama.cpp/commit/73e53dc834c0a2336cd104473af6897197b96277).
|
43 |
+
|
44 |
+
## Our projects
|
45 |
+
<table border="1" cellspacing="0" cellpadding="10">
|
46 |
+
<tr>
|
47 |
+
<th colspan="2" style="font-size: 25px;">Forge</th>
|
48 |
+
</tr>
|
49 |
+
<tr>
|
50 |
+
<th colspan="2">
|
51 |
+
<img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/>
|
52 |
+
</th>
|
53 |
+
</tr>
|
54 |
+
<tr>
|
55 |
+
<th colspan="2">An OpenAI-compatible multi-provider routing layer.</th>
|
56 |
+
</tr>
|
57 |
+
<tr>
|
58 |
+
<th colspan="2">
|
59 |
+
<a href="https://github.com/TensorBlock/forge" target="_blank" style="
|
60 |
+
display: inline-block;
|
61 |
+
padding: 8px 16px;
|
62 |
+
background-color: #FF7F50;
|
63 |
+
color: white;
|
64 |
+
text-decoration: none;
|
65 |
+
border-radius: 6px;
|
66 |
+
font-weight: bold;
|
67 |
+
font-family: sans-serif;
|
68 |
+
">π Try it now! π</a>
|
69 |
+
</th>
|
70 |
+
</tr>
|
71 |
+
|
72 |
+
<tr>
|
73 |
+
<th style="font-size: 25px;">Awesome MCP Servers</th>
|
74 |
+
<th style="font-size: 25px;">TensorBlock Studio</th>
|
75 |
+
</tr>
|
76 |
+
<tr>
|
77 |
+
<th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th>
|
78 |
+
<th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th>
|
79 |
+
</tr>
|
80 |
+
<tr>
|
81 |
+
<th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
|
82 |
+
<th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
|
83 |
+
</tr>
|
84 |
+
<tr>
|
85 |
+
<th>
|
86 |
+
<a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
|
87 |
+
display: inline-block;
|
88 |
+
padding: 8px 16px;
|
89 |
+
background-color: #FF7F50;
|
90 |
+
color: white;
|
91 |
+
text-decoration: none;
|
92 |
+
border-radius: 6px;
|
93 |
+
font-weight: bold;
|
94 |
+
font-family: sans-serif;
|
95 |
+
">π See what we built π</a>
|
96 |
+
</th>
|
97 |
+
<th>
|
98 |
+
<a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
|
99 |
+
display: inline-block;
|
100 |
+
padding: 8px 16px;
|
101 |
+
background-color: #FF7F50;
|
102 |
+
color: white;
|
103 |
+
text-decoration: none;
|
104 |
+
border-radius: 6px;
|
105 |
+
font-weight: bold;
|
106 |
+
font-family: sans-serif;
|
107 |
+
">π See what we built π</a>
|
108 |
+
</th>
|
109 |
+
</tr>
|
110 |
+
</table>
|
111 |
+
|
112 |
+
## Prompt template
|
113 |
+
|
114 |
+
```
|
115 |
+
{system_prompt}<|endoftext|>{prompt}<start_working_out>
|
116 |
+
```
|
117 |
+
|
118 |
+
## Model file specification
|
119 |
+
|
120 |
+
| Filename | Quant type | File Size | Description |
|
121 |
+
| -------- | ---------- | --------- | ----------- |
|
122 |
+
| [Qwen3_Medical_GRPO-Q2_K.gguf](https://huggingface.co/tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF/blob/main/Qwen3_Medical_GRPO-Q2_K.gguf) | Q2_K | 1.669 GB | smallest, significant quality loss - not recommended for most purposes |
|
123 |
+
| [Qwen3_Medical_GRPO-Q3_K_S.gguf](https://huggingface.co/tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF/blob/main/Qwen3_Medical_GRPO-Q3_K_S.gguf) | Q3_K_S | 1.887 GB | very small, high quality loss |
|
124 |
+
| [Qwen3_Medical_GRPO-Q3_K_M.gguf](https://huggingface.co/tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF/blob/main/Qwen3_Medical_GRPO-Q3_K_M.gguf) | Q3_K_M | 2.076 GB | very small, high quality loss |
|
125 |
+
| [Qwen3_Medical_GRPO-Q3_K_L.gguf](https://huggingface.co/tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF/blob/main/Qwen3_Medical_GRPO-Q3_K_L.gguf) | Q3_K_L | 2.240 GB | small, substantial quality loss |
|
126 |
+
| [Qwen3_Medical_GRPO-Q4_0.gguf](https://huggingface.co/tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF/blob/main/Qwen3_Medical_GRPO-Q4_0.gguf) | Q4_0 | 2.370 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
127 |
+
| [Qwen3_Medical_GRPO-Q4_K_S.gguf](https://huggingface.co/tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF/blob/main/Qwen3_Medical_GRPO-Q4_K_S.gguf) | Q4_K_S | 2.383 GB | small, greater quality loss |
|
128 |
+
| [Qwen3_Medical_GRPO-Q4_K_M.gguf](https://huggingface.co/tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF/blob/main/Qwen3_Medical_GRPO-Q4_K_M.gguf) | Q4_K_M | 2.497 GB | medium, balanced quality - recommended |
|
129 |
+
| [Qwen3_Medical_GRPO-Q5_0.gguf](https://huggingface.co/tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF/blob/main/Qwen3_Medical_GRPO-Q5_0.gguf) | Q5_0 | 2.824 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
130 |
+
| [Qwen3_Medical_GRPO-Q5_K_S.gguf](https://huggingface.co/tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF/blob/main/Qwen3_Medical_GRPO-Q5_K_S.gguf) | Q5_K_S | 2.824 GB | large, low quality loss - recommended |
|
131 |
+
| [Qwen3_Medical_GRPO-Q5_K_M.gguf](https://huggingface.co/tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF/blob/main/Qwen3_Medical_GRPO-Q5_K_M.gguf) | Q5_K_M | 2.890 GB | large, very low quality loss - recommended |
|
132 |
+
| [Qwen3_Medical_GRPO-Q6_K.gguf](https://huggingface.co/tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF/blob/main/Qwen3_Medical_GRPO-Q6_K.gguf) | Q6_K | 3.306 GB | very large, extremely low quality loss |
|
133 |
+
| [Qwen3_Medical_GRPO-Q8_0.gguf](https://huggingface.co/tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF/blob/main/Qwen3_Medical_GRPO-Q8_0.gguf) | Q8_0 | 4.280 GB | very large, extremely low quality loss - not recommended |
|
134 |
+
|
135 |
+
|
136 |
+
## Downloading instruction
|
137 |
+
|
138 |
+
### Command line
|
139 |
+
|
140 |
+
Firstly, install Huggingface Client
|
141 |
+
|
142 |
+
```shell
|
143 |
+
pip install -U "huggingface_hub[cli]"
|
144 |
+
```
|
145 |
+
|
146 |
+
Then, downoad the individual model file the a local directory
|
147 |
+
|
148 |
+
```shell
|
149 |
+
huggingface-cli download tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF --include "Qwen3_Medical_GRPO-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
150 |
+
```
|
151 |
+
|
152 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
153 |
+
|
154 |
+
```shell
|
155 |
+
huggingface-cli download tensorblock/lastmass_Qwen3_Medical_GRPO-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
156 |
+
```
|