Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Llama-Primus-Reasoning-Q2_K.gguf +3 -0
- Llama-Primus-Reasoning-Q3_K_L.gguf +3 -0
- Llama-Primus-Reasoning-Q3_K_M.gguf +3 -0
- Llama-Primus-Reasoning-Q3_K_S.gguf +3 -0
- Llama-Primus-Reasoning-Q4_0.gguf +3 -0
- Llama-Primus-Reasoning-Q4_K_M.gguf +3 -0
- Llama-Primus-Reasoning-Q4_K_S.gguf +3 -0
- Llama-Primus-Reasoning-Q5_0.gguf +3 -0
- Llama-Primus-Reasoning-Q5_K_M.gguf +3 -0
- Llama-Primus-Reasoning-Q5_K_S.gguf +3 -0
- Llama-Primus-Reasoning-Q6_K.gguf +3 -0
- Llama-Primus-Reasoning-Q8_0.gguf +3 -0
- README.md +148 -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-Primus-Reasoning-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Llama-Primus-Reasoning-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Llama-Primus-Reasoning-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Llama-Primus-Reasoning-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Llama-Primus-Reasoning-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Llama-Primus-Reasoning-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Llama-Primus-Reasoning-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Llama-Primus-Reasoning-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Llama-Primus-Reasoning-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Llama-Primus-Reasoning-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Llama-Primus-Reasoning-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Llama-Primus-Reasoning-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Llama-Primus-Reasoning-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef7052543ef9e970d5bb478b9f79a8277b2bff71d787c1105e28c1eb5dfc769f
|
3 |
+
size 3179133280
|
Llama-Primus-Reasoning-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:205a5ede3cf13bc2c2f40507ef67ada1a99e766b363597b64a3cf8fa707a10e5
|
3 |
+
size 4321958240
|
Llama-Primus-Reasoning-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03ad613ae72c23cffe8b86f6f71e86c70b0f6018af4823a2c09324b773f577db
|
3 |
+
size 4018919776
|
Llama-Primus-Reasoning-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0c0927283fe2fcc2e8cf5d45c733d782141d21c8bd2b3a147635b3e68fb4a8f
|
3 |
+
size 3664501088
|
Llama-Primus-Reasoning-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:719bfb2b20b6608a4062cb65b9d4c02ac3f35bcdfaf981bb071e006745ceda6e
|
3 |
+
size 4661213536
|
Llama-Primus-Reasoning-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e53f0a2ae5c59fecdc214984b00e7848199ebf7830a082bee5c9c680f46b86b0
|
3 |
+
size 4920736096
|
Llama-Primus-Reasoning-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99a139ccd46ba3e7c2838118120b0f7384bfab62f8d1a7ce9efea13a103c66a6
|
3 |
+
size 4692670816
|
Llama-Primus-Reasoning-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fd1ac1fcd376cd68804f13780e9ae9973213b59ad8f615012630bcfb452f3e0
|
3 |
+
size 5599295840
|
Llama-Primus-Reasoning-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1feb15011b2be45409284599ceae1fdd19ee15ebd57325f5fe6f6d19f788cf68
|
3 |
+
size 5732989280
|
Llama-Primus-Reasoning-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecc867083afad1fd61efaacb08a7b8f722101e0c15ffe5d1a91b1ceef415bc54
|
3 |
+
size 5599295840
|
Llama-Primus-Reasoning-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:937144646179f9dd44d12fc98622cbf28498be8ed697b38f4eaf6939c1848247
|
3 |
+
size 6596008288
|
Llama-Primus-Reasoning-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc0db5440f1acaaaed55b18295904ec4b40009e968cac80551e9f5d0822868dc
|
3 |
+
size 8540772704
|
README.md
ADDED
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
datasets:
|
4 |
+
- trendmicro-ailab/Primus-Reasoning
|
5 |
+
- trendmicro-ailab/Primus-Seed
|
6 |
+
- trendmicro-ailab/Primus-FineWeb
|
7 |
+
- trendmicro-ailab/Primus-Instruct
|
8 |
+
language:
|
9 |
+
- en
|
10 |
+
base_model: trendmicro-ailab/Llama-Primus-Reasoning
|
11 |
+
pipeline_tag: text-generation
|
12 |
+
library_name: transformers
|
13 |
+
tags:
|
14 |
+
- cybersecurity
|
15 |
+
- pretraining
|
16 |
+
- TensorBlock
|
17 |
+
- GGUF
|
18 |
+
extra_gated_fields:
|
19 |
+
Affiliation: text
|
20 |
+
Country: country
|
21 |
+
I want to use this model for:
|
22 |
+
type: select
|
23 |
+
options:
|
24 |
+
- Research
|
25 |
+
- Commercial
|
26 |
+
- label: Other
|
27 |
+
value: other
|
28 |
+
Job title:
|
29 |
+
type: select
|
30 |
+
options:
|
31 |
+
- Student
|
32 |
+
- Research graduate
|
33 |
+
- AI researcher
|
34 |
+
- AI developer/engineer
|
35 |
+
- Cybersecurity researcher
|
36 |
+
- Reporter
|
37 |
+
- Other
|
38 |
+
geo: ip_location
|
39 |
+
---
|
40 |
+
|
41 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
42 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
43 |
+
</div>
|
44 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
45 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
46 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
47 |
+
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>
|
48 |
+
</p>
|
49 |
+
</div>
|
50 |
+
</div>
|
51 |
+
|
52 |
+
## trendmicro-ailab/Llama-Primus-Reasoning - GGUF
|
53 |
+
|
54 |
+
This repo contains GGUF format model files for [trendmicro-ailab/Llama-Primus-Reasoning](https://huggingface.co/trendmicro-ailab/Llama-Primus-Reasoning).
|
55 |
+
|
56 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5165](https://github.com/ggml-org/llama.cpp/commit/1d735c0b4fa0551c51c2f4ac888dd9a01f447985).
|
57 |
+
|
58 |
+
## Our projects
|
59 |
+
<table border="1" cellspacing="0" cellpadding="10">
|
60 |
+
<tr>
|
61 |
+
<th style="font-size: 25px;">Awesome MCP Servers</th>
|
62 |
+
<th style="font-size: 25px;">TensorBlock Studio</th>
|
63 |
+
</tr>
|
64 |
+
<tr>
|
65 |
+
<th><img src="https://imgur.com/2Xov7B7.jpeg" alt="Project A" width="450"/></th>
|
66 |
+
<th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Project B" width="450"/></th>
|
67 |
+
</tr>
|
68 |
+
<tr>
|
69 |
+
<th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
|
70 |
+
<th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
|
71 |
+
</tr>
|
72 |
+
<tr>
|
73 |
+
<th>
|
74 |
+
<a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
|
75 |
+
display: inline-block;
|
76 |
+
padding: 8px 16px;
|
77 |
+
background-color: #FF7F50;
|
78 |
+
color: white;
|
79 |
+
text-decoration: none;
|
80 |
+
border-radius: 6px;
|
81 |
+
font-weight: bold;
|
82 |
+
font-family: sans-serif;
|
83 |
+
">π See what we built π</a>
|
84 |
+
</th>
|
85 |
+
<th>
|
86 |
+
<a href="https://github.com/TensorBlock/TensorBlock-Studio" 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 |
+
</tr>
|
98 |
+
</table>
|
99 |
+
|
100 |
+
## Prompt template
|
101 |
+
|
102 |
+
```
|
103 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
104 |
+
|
105 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
106 |
+
|
107 |
+
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
108 |
+
```
|
109 |
+
|
110 |
+
## Model file specification
|
111 |
+
|
112 |
+
| Filename | Quant type | File Size | Description |
|
113 |
+
| -------- | ---------- | --------- | ----------- |
|
114 |
+
| [Llama-Primus-Reasoning-Q2_K.gguf](https://huggingface.co/tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF/blob/main/Llama-Primus-Reasoning-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
|
115 |
+
| [Llama-Primus-Reasoning-Q3_K_S.gguf](https://huggingface.co/tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF/blob/main/Llama-Primus-Reasoning-Q3_K_S.gguf) | Q3_K_S | 3.665 GB | very small, high quality loss |
|
116 |
+
| [Llama-Primus-Reasoning-Q3_K_M.gguf](https://huggingface.co/tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF/blob/main/Llama-Primus-Reasoning-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
|
117 |
+
| [Llama-Primus-Reasoning-Q3_K_L.gguf](https://huggingface.co/tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF/blob/main/Llama-Primus-Reasoning-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
|
118 |
+
| [Llama-Primus-Reasoning-Q4_0.gguf](https://huggingface.co/tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF/blob/main/Llama-Primus-Reasoning-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
119 |
+
| [Llama-Primus-Reasoning-Q4_K_S.gguf](https://huggingface.co/tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF/blob/main/Llama-Primus-Reasoning-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss |
|
120 |
+
| [Llama-Primus-Reasoning-Q4_K_M.gguf](https://huggingface.co/tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF/blob/main/Llama-Primus-Reasoning-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |
|
121 |
+
| [Llama-Primus-Reasoning-Q5_0.gguf](https://huggingface.co/tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF/blob/main/Llama-Primus-Reasoning-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
122 |
+
| [Llama-Primus-Reasoning-Q5_K_S.gguf](https://huggingface.co/tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF/blob/main/Llama-Primus-Reasoning-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended |
|
123 |
+
| [Llama-Primus-Reasoning-Q5_K_M.gguf](https://huggingface.co/tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF/blob/main/Llama-Primus-Reasoning-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |
|
124 |
+
| [Llama-Primus-Reasoning-Q6_K.gguf](https://huggingface.co/tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF/blob/main/Llama-Primus-Reasoning-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss |
|
125 |
+
| [Llama-Primus-Reasoning-Q8_0.gguf](https://huggingface.co/tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF/blob/main/Llama-Primus-Reasoning-Q8_0.gguf) | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended |
|
126 |
+
|
127 |
+
|
128 |
+
## Downloading instruction
|
129 |
+
|
130 |
+
### Command line
|
131 |
+
|
132 |
+
Firstly, install Huggingface Client
|
133 |
+
|
134 |
+
```shell
|
135 |
+
pip install -U "huggingface_hub[cli]"
|
136 |
+
```
|
137 |
+
|
138 |
+
Then, downoad the individual model file the a local directory
|
139 |
+
|
140 |
+
```shell
|
141 |
+
huggingface-cli download tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF --include "Llama-Primus-Reasoning-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
142 |
+
```
|
143 |
+
|
144 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
145 |
+
|
146 |
+
```shell
|
147 |
+
huggingface-cli download tensorblock/trendmicro-ailab_Llama-Primus-Reasoning-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
148 |
+
```
|