morriszms commited on
Commit
50f0e72
·
verified ·
1 Parent(s): 6379837

Upload folder using huggingface_hub

Browse files
.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-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Phi-4-mini-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Phi-4-mini-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Phi-4-mini-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Phi-4-mini-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Phi-4-mini-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Phi-4-mini-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Phi-4-mini-instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Phi-4-mini-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Phi-4-mini-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Phi-4-mini-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Phi-4-mini-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Phi-4-mini-instruct-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295c3972f54c20a47d571495f167db7e02c4981207f03e51d5c00479a374f3b3
3
+ size 1682636096
Phi-4-mini-instruct-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76cc1941ccad9f14c987b4ec12cab07c5312de6dec46dc5dd8b45170675c7698
3
+ size 2249653568
Phi-4-mini-instruct-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e0aae476fc464b8635c08fe50f355e3f096b98328fe520073800c4b211bdbc
3
+ size 2117532992
Phi-4-mini-instruct-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3392e587db39e5efd86812484b4f09ea84f43324b8dafd9741434404928819fa
3
+ size 1897332032
Phi-4-mini-instruct-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59eb0cc05b6af62a240c6ef0b9c755920b729d85bc7bbee354b2511cadf9bc95
3
+ size 2325151040
Phi-4-mini-instruct-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55239fbd0dc947146be056e7850d2fa3a55d0091aa2cc873767e686c3b15eeed
3
+ size 2491874624
Phi-4-mini-instruct-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:332b24022d5f2343897b18ea33c23fce7b44682620bc7667f05ab76a10690bd8
3
+ size 2337733952
Phi-4-mini-instruct-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b1d2c9f4cb7a11e908d5d6bd8e07f3ea26f9228a8b38f61ddc819a86d1501eb
3
+ size 2727804224
Phi-4-mini-instruct-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e7555f68a3762f25ebba4acaac7f303979aa88eebf862f1f8a561103c9af70
3
+ size 2848128320
Phi-4-mini-instruct-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b258b9e38595ff3960657bf789e2de8651b0b60cfa36a6cef9a4d17a7734a0dc
3
+ size 2727804224
Phi-4-mini-instruct-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172f36acd48986a382d78d98d6816f767c791e926a02bf7ac541e7cf58b51c28
3
+ size 3155623232
Phi-4-mini-instruct-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f3992305494d7d61267924a357f6d0f9e68035a38aa589cff386c09ee52bc9
3
+ size 4084611392
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct/resolve/main/LICENSE
4
+ language:
5
+ - multilingual
6
+ - ar
7
+ - zh
8
+ - cs
9
+ - da
10
+ - nl
11
+ - en
12
+ - fi
13
+ - fr
14
+ - de
15
+ - he
16
+ - hu
17
+ - it
18
+ - ja
19
+ - ko
20
+ - 'no'
21
+ - pl
22
+ - pt
23
+ - ru
24
+ - es
25
+ - sv
26
+ - th
27
+ - tr
28
+ - uk
29
+ pipeline_tag: text-generation
30
+ tags:
31
+ - nlp
32
+ - code
33
+ - TensorBlock
34
+ - GGUF
35
+ widget:
36
+ - messages:
37
+ - role: user
38
+ content: Can you provide ways to eat combinations of bananas and dragonfruits?
39
+ library_name: transformers
40
+ base_model: microsoft/Phi-4-mini-instruct
41
+ ---
42
+
43
+ <div style="width: auto; margin-left: auto; margin-right: auto">
44
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
45
+ </div>
46
+ <div style="display: flex; justify-content: space-between; width: 100%;">
47
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
48
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
49
+ 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>
50
+ </p>
51
+ </div>
52
+ </div>
53
+
54
+ ## microsoft/Phi-4-mini-instruct - GGUF
55
+
56
+ This repo contains GGUF format model files for [microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct).
57
+
58
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4823](https://github.com/ggml-org/llama.cpp/commit/5bbe6a9fe9a8796a9389c85accec89dbc4d91e39).
59
+
60
+ <div style="text-align: left; margin: 20px 0;">
61
+ <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
62
+ Run them on the TensorBlock client using your local machine ↗
63
+ </a>
64
+ </div>
65
+
66
+ ## Prompt template
67
+
68
+ ```
69
+ <|system|>{system_prompt}<|end|><|user|>{prompt}<|end|><|assistant|>
70
+ ```
71
+
72
+ ## Model file specification
73
+
74
+ | Filename | Quant type | File Size | Description |
75
+ | -------- | ---------- | --------- | ----------- |
76
+ | [Phi-4-mini-instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q2_K.gguf) | Q2_K | 1.683 GB | smallest, significant quality loss - not recommended for most purposes |
77
+ | [Phi-4-mini-instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q3_K_S.gguf) | Q3_K_S | 1.897 GB | very small, high quality loss |
78
+ | [Phi-4-mini-instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q3_K_M.gguf) | Q3_K_M | 2.118 GB | very small, high quality loss |
79
+ | [Phi-4-mini-instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q3_K_L.gguf) | Q3_K_L | 2.250 GB | small, substantial quality loss |
80
+ | [Phi-4-mini-instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q4_0.gguf) | Q4_0 | 2.325 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
81
+ | [Phi-4-mini-instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q4_K_S.gguf) | Q4_K_S | 2.338 GB | small, greater quality loss |
82
+ | [Phi-4-mini-instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q4_K_M.gguf) | Q4_K_M | 2.492 GB | medium, balanced quality - recommended |
83
+ | [Phi-4-mini-instruct-Q5_0.gguf](https://huggingface.co/tensorblock/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q5_0.gguf) | Q5_0 | 2.728 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
84
+ | [Phi-4-mini-instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q5_K_S.gguf) | Q5_K_S | 2.728 GB | large, low quality loss - recommended |
85
+ | [Phi-4-mini-instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q5_K_M.gguf) | Q5_K_M | 2.848 GB | large, very low quality loss - recommended |
86
+ | [Phi-4-mini-instruct-Q6_K.gguf](https://huggingface.co/tensorblock/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q6_K.gguf) | Q6_K | 3.156 GB | very large, extremely low quality loss |
87
+ | [Phi-4-mini-instruct-Q8_0.gguf](https://huggingface.co/tensorblock/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q8_0.gguf) | Q8_0 | 4.085 GB | very large, extremely low quality loss - not recommended |
88
+
89
+
90
+ ## Downloading instruction
91
+
92
+ ### Command line
93
+
94
+ Firstly, install Huggingface Client
95
+
96
+ ```shell
97
+ pip install -U "huggingface_hub[cli]"
98
+ ```
99
+
100
+ Then, downoad the individual model file the a local directory
101
+
102
+ ```shell
103
+ huggingface-cli download tensorblock/Phi-4-mini-instruct-GGUF --include "Phi-4-mini-instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
104
+ ```
105
+
106
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
107
+
108
+ ```shell
109
+ huggingface-cli download tensorblock/Phi-4-mini-instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
110
+ ```