Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Phi-3-medium-128k-instruct-Q2_K.gguf +3 -0
- Phi-3-medium-128k-instruct-Q3_K_L.gguf +3 -0
- Phi-3-medium-128k-instruct-Q3_K_M.gguf +3 -0
- Phi-3-medium-128k-instruct-Q3_K_S.gguf +3 -0
- Phi-3-medium-128k-instruct-Q4_0.gguf +3 -0
- Phi-3-medium-128k-instruct-Q4_K_M.gguf +3 -0
- Phi-3-medium-128k-instruct-Q4_K_S.gguf +3 -0
- Phi-3-medium-128k-instruct-Q5_0.gguf +3 -0
- Phi-3-medium-128k-instruct-Q5_K_M.gguf +3 -0
- Phi-3-medium-128k-instruct-Q5_K_S.gguf +3 -0
- Phi-3-medium-128k-instruct-Q6_K.gguf +3 -0
- Phi-3-medium-128k-instruct-Q8_0.gguf +3 -0
- README.md +85 -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-3-medium-128k-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Phi-3-medium-128k-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Phi-3-medium-128k-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Phi-3-medium-128k-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Phi-3-medium-128k-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Phi-3-medium-128k-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Phi-3-medium-128k-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Phi-3-medium-128k-instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Phi-3-medium-128k-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Phi-3-medium-128k-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Phi-3-medium-128k-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Phi-3-medium-128k-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Phi-3-medium-128k-instruct-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:665011da2e293879b2207c95716c6ccbc99d032abf7ced8d0779ec05d8f74308
|
3 |
+
size 5143000864
|
Phi-3-medium-128k-instruct-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74d759441457c7a77096b1ebb31218e6bb24f05ee3934c535e181657194fb9e2
|
3 |
+
size 7490298144
|
Phi-3-medium-128k-instruct-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e9b83747f92a9d3665e907865555548d20e111689588825cb12228d1a6b66a6
|
3 |
+
size 6923411744
|
Phi-3-medium-128k-instruct-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7bf4b6ce8c862ddff88b3e7077a065ee677b61f54d041d60c5d3e6d065ad7d7
|
3 |
+
size 6064890144
|
Phi-3-medium-128k-instruct-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0aeb25b81f81ef2ea0a1e305455a6498919d2e0cb51aa950afd553aba32aad29
|
3 |
+
size 7897125664
|
Phi-3-medium-128k-instruct-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:418c6ee87c1a6d1709e0f1181192296fa2905416574498ebad85ccf657f6bc0b
|
3 |
+
size 8566821664
|
Phi-3-medium-128k-instruct-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19abb2672904b07054ff1e3f03aaaa434ddbe18d185993fe9747a4488294c371
|
3 |
+
size 7954469664
|
Phi-3-medium-128k-instruct-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:600a84211e2ff6ad14f71b8d1151f79895aea852332cf0ac4208b5fa67e31e56
|
3 |
+
size 9621582624
|
Phi-3-medium-128k-instruct-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f2d3f997bed4bfb91af42400cb93df2b6a2cfd87e161079cede785018fe41d2
|
3 |
+
size 10074190624
|
Phi-3-medium-128k-instruct-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8180477db81640fac71ad0df1ea4805b00e240604beff314233c05c79222938
|
3 |
+
size 9621582624
|
Phi-3-medium-128k-instruct-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07ef6156d163b024525dcb25058589362f4bc7e7e27f0a6c8aa2755bac739a3e
|
3 |
+
size 11453818144
|
Phi-3-medium-128k-instruct-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49a0c65e69667d860bd75ade5f240590f056d1d7847d6b75fdc2eaacda42050e
|
3 |
+
size 14834712864
|
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
license_link: https://huggingface.co/microsoft/Phi-3-medium-128k-instruct/resolve/main/LICENSE
|
4 |
+
language:
|
5 |
+
- multilingual
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
tags:
|
8 |
+
- nlp
|
9 |
+
- code
|
10 |
+
- TensorBlock
|
11 |
+
- GGUF
|
12 |
+
inference:
|
13 |
+
parameters:
|
14 |
+
temperature: 0.7
|
15 |
+
widget:
|
16 |
+
- messages:
|
17 |
+
- role: user
|
18 |
+
content: Can you provide ways to eat combinations of bananas and dragonfruits?
|
19 |
+
base_model: microsoft/Phi-3-medium-128k-instruct
|
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 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
26 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
27 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
28 |
+
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>
|
29 |
+
</p>
|
30 |
+
</div>
|
31 |
+
</div>
|
32 |
+
|
33 |
+
## microsoft/Phi-3-medium-128k-instruct - GGUF
|
34 |
+
|
35 |
+
This repo contains GGUF format model files for [microsoft/Phi-3-medium-128k-instruct](https://huggingface.co/microsoft/Phi-3-medium-128k-instruct).
|
36 |
+
|
37 |
+
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).
|
38 |
+
|
39 |
+
## Prompt template
|
40 |
+
|
41 |
+
```
|
42 |
+
<|user|>
|
43 |
+
{prompt}<|end|>
|
44 |
+
<|assistant|>
|
45 |
+
```
|
46 |
+
|
47 |
+
## Model file specification
|
48 |
+
|
49 |
+
| Filename | Quant type | File Size | Description |
|
50 |
+
| -------- | ---------- | --------- | ----------- |
|
51 |
+
| [Phi-3-medium-128k-instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Phi-3-medium-128k-instruct-GGUF/tree/main/Phi-3-medium-128k-instruct-Q2_K.gguf) | Q2_K | 4.790 GB | smallest, significant quality loss - not recommended for most purposes |
|
52 |
+
| [Phi-3-medium-128k-instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Phi-3-medium-128k-instruct-GGUF/tree/main/Phi-3-medium-128k-instruct-Q3_K_S.gguf) | Q3_K_S | 5.648 GB | very small, high quality loss |
|
53 |
+
| [Phi-3-medium-128k-instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Phi-3-medium-128k-instruct-GGUF/tree/main/Phi-3-medium-128k-instruct-Q3_K_M.gguf) | Q3_K_M | 6.448 GB | very small, high quality loss |
|
54 |
+
| [Phi-3-medium-128k-instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Phi-3-medium-128k-instruct-GGUF/tree/main/Phi-3-medium-128k-instruct-Q3_K_L.gguf) | Q3_K_L | 6.976 GB | small, substantial quality loss |
|
55 |
+
| [Phi-3-medium-128k-instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Phi-3-medium-128k-instruct-GGUF/tree/main/Phi-3-medium-128k-instruct-Q4_0.gguf) | Q4_0 | 7.355 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
56 |
+
| [Phi-3-medium-128k-instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/Phi-3-medium-128k-instruct-GGUF/tree/main/Phi-3-medium-128k-instruct-Q4_K_S.gguf) | Q4_K_S | 7.408 GB | small, greater quality loss |
|
57 |
+
| [Phi-3-medium-128k-instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/Phi-3-medium-128k-instruct-GGUF/tree/main/Phi-3-medium-128k-instruct-Q4_K_M.gguf) | Q4_K_M | 7.978 GB | medium, balanced quality - recommended |
|
58 |
+
| [Phi-3-medium-128k-instruct-Q5_0.gguf](https://huggingface.co/tensorblock/Phi-3-medium-128k-instruct-GGUF/tree/main/Phi-3-medium-128k-instruct-Q5_0.gguf) | Q5_0 | 8.961 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
59 |
+
| [Phi-3-medium-128k-instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/Phi-3-medium-128k-instruct-GGUF/tree/main/Phi-3-medium-128k-instruct-Q5_K_S.gguf) | Q5_K_S | 8.961 GB | large, low quality loss - recommended |
|
60 |
+
| [Phi-3-medium-128k-instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/Phi-3-medium-128k-instruct-GGUF/tree/main/Phi-3-medium-128k-instruct-Q5_K_M.gguf) | Q5_K_M | 9.382 GB | large, very low quality loss - recommended |
|
61 |
+
| [Phi-3-medium-128k-instruct-Q6_K.gguf](https://huggingface.co/tensorblock/Phi-3-medium-128k-instruct-GGUF/tree/main/Phi-3-medium-128k-instruct-Q6_K.gguf) | Q6_K | 10.667 GB | very large, extremely low quality loss |
|
62 |
+
| [Phi-3-medium-128k-instruct-Q8_0.gguf](https://huggingface.co/tensorblock/Phi-3-medium-128k-instruct-GGUF/tree/main/Phi-3-medium-128k-instruct-Q8_0.gguf) | Q8_0 | 13.816 GB | very large, extremely low quality loss - not recommended |
|
63 |
+
|
64 |
+
|
65 |
+
## Downloading instruction
|
66 |
+
|
67 |
+
### Command line
|
68 |
+
|
69 |
+
Firstly, install Huggingface Client
|
70 |
+
|
71 |
+
```shell
|
72 |
+
pip install -U "huggingface_hub[cli]"
|
73 |
+
```
|
74 |
+
|
75 |
+
Then, downoad the individual model file the a local directory
|
76 |
+
|
77 |
+
```shell
|
78 |
+
huggingface-cli download tensorblock/Phi-3-medium-128k-instruct-GGUF --include "Phi-3-medium-128k-instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
79 |
+
```
|
80 |
+
|
81 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
82 |
+
|
83 |
+
```shell
|
84 |
+
huggingface-cli download tensorblock/Phi-3-medium-128k-instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
85 |
+
```
|