Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Phi-4-mini-reasoning-Q2_K.gguf +3 -0
- Phi-4-mini-reasoning-Q3_K_L.gguf +3 -0
- Phi-4-mini-reasoning-Q3_K_M.gguf +3 -0
- Phi-4-mini-reasoning-Q3_K_S.gguf +3 -0
- Phi-4-mini-reasoning-Q4_0.gguf +3 -0
- Phi-4-mini-reasoning-Q4_K_M.gguf +3 -0
- Phi-4-mini-reasoning-Q4_K_S.gguf +3 -0
- Phi-4-mini-reasoning-Q5_0.gguf +3 -0
- Phi-4-mini-reasoning-Q5_K_M.gguf +3 -0
- Phi-4-mini-reasoning-Q5_K_S.gguf +3 -0
- Phi-4-mini-reasoning-Q6_K.gguf +3 -0
- Phi-4-mini-reasoning-Q8_0.gguf +3 -0
- README.md +157 -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 |
+
Phi-4-mini-reasoning-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Phi-4-mini-reasoning-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Phi-4-mini-reasoning-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Phi-4-mini-reasoning-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Phi-4-mini-reasoning-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Phi-4-mini-reasoning-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Phi-4-mini-reasoning-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Phi-4-mini-reasoning-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Phi-4-mini-reasoning-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Phi-4-mini-reasoning-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Phi-4-mini-reasoning-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Phi-4-mini-reasoning-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Phi-4-mini-reasoning-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3b8a4186816cf066a3e6db6baf7e71039355ad75437484820d48004f560a086
|
3 |
+
size 1682636352
|
Phi-4-mini-reasoning-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:415e1f231e34c6fca40493ceda3c2b7a53e5243a017c3ea06d70ff62b9c7afb9
|
3 |
+
size 2249653824
|
Phi-4-mini-reasoning-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28b128f29ff9454892c7f096076b298d7e85469a666060b4f636926fbf88a04b
|
3 |
+
size 2117533248
|
Phi-4-mini-reasoning-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d06118ef52167db7a327a160469119d311446cd1f68de977d7a1be9b8b28245e
|
3 |
+
size 1897332288
|
Phi-4-mini-reasoning-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c55706c93bd904169c2273249e32c40ded2eccbb7e47bd11f9366e83dca5c0e
|
3 |
+
size 2325151296
|
Phi-4-mini-reasoning-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4854bbe1e16b1cec28ea6878c961c04ae4e4e5d7fb6a33a7b791e1f5e656ff6b
|
3 |
+
size 2491874880
|
Phi-4-mini-reasoning-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc9215f3e637150976e8c955bcca1b1d5a0b2e515f11506c68f41be1df69f07d
|
3 |
+
size 2337734208
|
Phi-4-mini-reasoning-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eab2b5bb8a1442d0b66d4e60c503332cc36b2feb20b4fff96174541c62a22e2c
|
3 |
+
size 2727804480
|
Phi-4-mini-reasoning-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8ed1798fa3bd6e6c494ffbe44c666b24708b2473437faeba562ec6567d2b72b
|
3 |
+
size 2848128576
|
Phi-4-mini-reasoning-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a774217c2b999cf4f9c768fae0c8b1f94c877fa200653d75a87f2da12222a55a
|
3 |
+
size 2727804480
|
Phi-4-mini-reasoning-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27d458a76ba2372de4bbc1a381aeb8eb6e0095e0041a7d328407c492f7c7ea8b
|
3 |
+
size 3155623488
|
Phi-4-mini-reasoning-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9a3d7c4adf4b2a2ae2d6679c4149355d281df3c3f715da6f82dcc0108594c88
|
3 |
+
size 4084611648
|
README.md
ADDED
@@ -0,0 +1,157 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: unsloth/Phi-4-mini-reasoning
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
library_name: transformers
|
6 |
+
license: mit
|
7 |
+
license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct-reasoning/resolve/main/LICENSE
|
8 |
+
pipeline_tag: text-generation
|
9 |
+
tags:
|
10 |
+
- nlp
|
11 |
+
- unsloth
|
12 |
+
- math
|
13 |
+
- code
|
14 |
+
- TensorBlock
|
15 |
+
- GGUF
|
16 |
+
widget:
|
17 |
+
- messages:
|
18 |
+
- role: user
|
19 |
+
content: How to solve 3*x^2+4*x+5=1?
|
20 |
+
---
|
21 |
+
|
22 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
23 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
24 |
+
</div>
|
25 |
+
|
26 |
+
[](https://tensorblock.co)
|
27 |
+
[](https://twitter.com/tensorblock_aoi)
|
28 |
+
[](https://discord.gg/Ej5NmeHFf2)
|
29 |
+
[](https://github.com/TensorBlock)
|
30 |
+
[](https://t.me/TensorBlock)
|
31 |
+
|
32 |
+
|
33 |
+
## unsloth/Phi-4-mini-reasoning - GGUF
|
34 |
+
|
35 |
+
<div style="text-align: left; margin: 20px 0;">
|
36 |
+
<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;">
|
37 |
+
Join our Discord to learn more about what we're building β
|
38 |
+
</a>
|
39 |
+
</div>
|
40 |
+
|
41 |
+
This repo contains GGUF format model files for [unsloth/Phi-4-mini-reasoning](https://huggingface.co/unsloth/Phi-4-mini-reasoning).
|
42 |
+
|
43 |
+
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).
|
44 |
+
|
45 |
+
## Our projects
|
46 |
+
<table border="1" cellspacing="0" cellpadding="10">
|
47 |
+
<tr>
|
48 |
+
<th colspan="2" style="font-size: 25px;">Forge</th>
|
49 |
+
</tr>
|
50 |
+
<tr>
|
51 |
+
<th colspan="2">
|
52 |
+
<img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/>
|
53 |
+
</th>
|
54 |
+
</tr>
|
55 |
+
<tr>
|
56 |
+
<th colspan="2">An OpenAI-compatible multi-provider routing layer.</th>
|
57 |
+
</tr>
|
58 |
+
<tr>
|
59 |
+
<th colspan="2">
|
60 |
+
<a href="https://github.com/TensorBlock/forge" target="_blank" style="
|
61 |
+
display: inline-block;
|
62 |
+
padding: 8px 16px;
|
63 |
+
background-color: #FF7F50;
|
64 |
+
color: white;
|
65 |
+
text-decoration: none;
|
66 |
+
border-radius: 6px;
|
67 |
+
font-weight: bold;
|
68 |
+
font-family: sans-serif;
|
69 |
+
">π Try it now! π</a>
|
70 |
+
</th>
|
71 |
+
</tr>
|
72 |
+
|
73 |
+
<tr>
|
74 |
+
<th style="font-size: 25px;">Awesome MCP Servers</th>
|
75 |
+
<th style="font-size: 25px;">TensorBlock Studio</th>
|
76 |
+
</tr>
|
77 |
+
<tr>
|
78 |
+
<th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th>
|
79 |
+
<th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th>
|
80 |
+
</tr>
|
81 |
+
<tr>
|
82 |
+
<th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
|
83 |
+
<th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
|
84 |
+
</tr>
|
85 |
+
<tr>
|
86 |
+
<th>
|
87 |
+
<a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
|
88 |
+
display: inline-block;
|
89 |
+
padding: 8px 16px;
|
90 |
+
background-color: #FF7F50;
|
91 |
+
color: white;
|
92 |
+
text-decoration: none;
|
93 |
+
border-radius: 6px;
|
94 |
+
font-weight: bold;
|
95 |
+
font-family: sans-serif;
|
96 |
+
">π See what we built π</a>
|
97 |
+
</th>
|
98 |
+
<th>
|
99 |
+
<a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
|
100 |
+
display: inline-block;
|
101 |
+
padding: 8px 16px;
|
102 |
+
background-color: #FF7F50;
|
103 |
+
color: white;
|
104 |
+
text-decoration: none;
|
105 |
+
border-radius: 6px;
|
106 |
+
font-weight: bold;
|
107 |
+
font-family: sans-serif;
|
108 |
+
">π See what we built π</a>
|
109 |
+
</th>
|
110 |
+
</tr>
|
111 |
+
</table>
|
112 |
+
|
113 |
+
## Prompt template
|
114 |
+
|
115 |
+
```
|
116 |
+
<|system|>Your name is Phi, an AI math expert developed by Microsoft. {system_prompt}<|end|><|user|>{prompt}<|end|><|assistant|>
|
117 |
+
```
|
118 |
+
|
119 |
+
## Model file specification
|
120 |
+
|
121 |
+
| Filename | Quant type | File Size | Description |
|
122 |
+
| -------- | ---------- | --------- | ----------- |
|
123 |
+
| [Phi-4-mini-reasoning-Q2_K.gguf](https://huggingface.co/tensorblock/unsloth_Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q2_K.gguf) | Q2_K | 1.683 GB | smallest, significant quality loss - not recommended for most purposes |
|
124 |
+
| [Phi-4-mini-reasoning-Q3_K_S.gguf](https://huggingface.co/tensorblock/unsloth_Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q3_K_S.gguf) | Q3_K_S | 1.897 GB | very small, high quality loss |
|
125 |
+
| [Phi-4-mini-reasoning-Q3_K_M.gguf](https://huggingface.co/tensorblock/unsloth_Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q3_K_M.gguf) | Q3_K_M | 2.118 GB | very small, high quality loss |
|
126 |
+
| [Phi-4-mini-reasoning-Q3_K_L.gguf](https://huggingface.co/tensorblock/unsloth_Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q3_K_L.gguf) | Q3_K_L | 2.250 GB | small, substantial quality loss |
|
127 |
+
| [Phi-4-mini-reasoning-Q4_0.gguf](https://huggingface.co/tensorblock/unsloth_Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q4_0.gguf) | Q4_0 | 2.325 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
128 |
+
| [Phi-4-mini-reasoning-Q4_K_S.gguf](https://huggingface.co/tensorblock/unsloth_Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q4_K_S.gguf) | Q4_K_S | 2.338 GB | small, greater quality loss |
|
129 |
+
| [Phi-4-mini-reasoning-Q4_K_M.gguf](https://huggingface.co/tensorblock/unsloth_Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q4_K_M.gguf) | Q4_K_M | 2.492 GB | medium, balanced quality - recommended |
|
130 |
+
| [Phi-4-mini-reasoning-Q5_0.gguf](https://huggingface.co/tensorblock/unsloth_Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q5_0.gguf) | Q5_0 | 2.728 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
131 |
+
| [Phi-4-mini-reasoning-Q5_K_S.gguf](https://huggingface.co/tensorblock/unsloth_Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q5_K_S.gguf) | Q5_K_S | 2.728 GB | large, low quality loss - recommended |
|
132 |
+
| [Phi-4-mini-reasoning-Q5_K_M.gguf](https://huggingface.co/tensorblock/unsloth_Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q5_K_M.gguf) | Q5_K_M | 2.848 GB | large, very low quality loss - recommended |
|
133 |
+
| [Phi-4-mini-reasoning-Q6_K.gguf](https://huggingface.co/tensorblock/unsloth_Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q6_K.gguf) | Q6_K | 3.156 GB | very large, extremely low quality loss |
|
134 |
+
| [Phi-4-mini-reasoning-Q8_0.gguf](https://huggingface.co/tensorblock/unsloth_Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q8_0.gguf) | Q8_0 | 4.085 GB | very large, extremely low quality loss - not recommended |
|
135 |
+
|
136 |
+
|
137 |
+
## Downloading instruction
|
138 |
+
|
139 |
+
### Command line
|
140 |
+
|
141 |
+
Firstly, install Huggingface Client
|
142 |
+
|
143 |
+
```shell
|
144 |
+
pip install -U "huggingface_hub[cli]"
|
145 |
+
```
|
146 |
+
|
147 |
+
Then, downoad the individual model file the a local directory
|
148 |
+
|
149 |
+
```shell
|
150 |
+
huggingface-cli download tensorblock/unsloth_Phi-4-mini-reasoning-GGUF --include "Phi-4-mini-reasoning-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
151 |
+
```
|
152 |
+
|
153 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
154 |
+
|
155 |
+
```shell
|
156 |
+
huggingface-cli download tensorblock/unsloth_Phi-4-mini-reasoning-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
157 |
+
```
|