Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- Phi-4-mini-instruct_multi-prefill-seq_q8_ekv1280.task +3 -0
- README.md +7 -4
.gitattributes
CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* 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 |
phi4_q8_ekv1280.task 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 |
phi4_q8_ekv1280.task filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Phi-4-mini-instruct_multi-prefill-seq_q8_ekv1280.task filter=lfs diff=lfs merge=lfs -text
|
Phi-4-mini-instruct_multi-prefill-seq_q8_ekv1280.task
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e494f9e827fbf47ac271d67dde77308f4a7683ad1ff630ab5bec926f17573b5f
|
3 |
+
size 3944275882
|
README.md
CHANGED
@@ -1,6 +1,9 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
base_model: microsoft/Phi-4-mini-instruct
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
# litert-community/Phi-4-mini-instruct
|
@@ -53,10 +56,10 @@ Note that all benchmark stats are from a Samsung S24 Ultra with
|
|
53 |
<tr>
|
54 |
<td>dynamic_int8</td>
|
55 |
<td>cpu</td>
|
56 |
-
<td><p style="text-align: right">
|
57 |
-
<td><p style="text-align: right">6.
|
58 |
-
<td><p style="text-align: right">
|
59 |
-
<td><p style="text-align: right">6,
|
60 |
<td><p style="text-align: right">3,761 MB</p></td>
|
61 |
</tr>
|
62 |
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
base_model: microsoft/Phi-4-mini-instruct
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- chat
|
7 |
---
|
8 |
|
9 |
# litert-community/Phi-4-mini-instruct
|
|
|
56 |
<tr>
|
57 |
<td>dynamic_int8</td>
|
58 |
<td>cpu</td>
|
59 |
+
<td><p style="text-align: right">55.60 tk/s</p></td>
|
60 |
+
<td><p style="text-align: right">6.08 tk/s</p></td>
|
61 |
+
<td><p style="text-align: right">16.66 s</p></td>
|
62 |
+
<td><p style="text-align: right">6,195 MB</p></td>
|
63 |
<td><p style="text-align: right">3,761 MB</p></td>
|
64 |
</tr>
|
65 |
|