filipealmeida
commited on
Commit
•
3e075fe
1
Parent(s):
78a654a
Upload folder using huggingface_hub (#2)
Browse files- Upload folder using huggingface_hub (cb4beba13bcfc3a01bf1ea812d50d064f2d4585c)
- .gitattributes +2 -0
- README.md +1 -7
- mpt-7b-instruct-Q4_0.gguf +3 -0
- mpt-7b-instruct-Q8_0.gguf +3 -0
.gitattributes
CHANGED
@@ -32,4 +32,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
35 |
mpt-7b-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
mpt-7b-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
36 |
+
mpt-7b-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
mpt-7b-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -11,15 +11,9 @@ inference: false
|
|
11 |
|
12 |
# MPT-7B-Instruct
|
13 |
|
14 |
-
<span style="color:red">This is not working yet with the official version of llama.cpp</span>
|
15 |
-
|
16 |
This is the GGUF version of MPT-7B-Instruct based on [jploski's fork of llama.cpp](https://github.com/jploski/llama.cpp)
|
17 |
|
18 |
-
Right now it only works with that branch, but hopefully
|
19 |
-
|
20 |
-
I needed this for some prototyping so I'll also maintain a fork of the python bindings while this isn't all merged in here: [llama-cpp-python-mpt](https://github.com/filipe-m-almeida/llama-cpp-python-mpt)
|
21 |
-
|
22 |
-
-----
|
23 |
|
24 |
MPT-7B-Instruct is a model for short-form instruction following.
|
25 |
It is built by finetuning [MPT-7B](https://huggingface.co/mosaicml/mpt-7b) on a [dataset](https://huggingface.co/datasets/sam-mosaic/dolly_hhrlhf) derived from the [Databricks Dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) and the [Anthropic Helpful and Harmless (HH-RLHF)](https://huggingface.co/datasets/Anthropic/hh-rlhf) datasets.
|
|
|
11 |
|
12 |
# MPT-7B-Instruct
|
13 |
|
|
|
|
|
14 |
This is the GGUF version of MPT-7B-Instruct based on [jploski's fork of llama.cpp](https://github.com/jploski/llama.cpp)
|
15 |
|
16 |
+
Right now it only works with that branch, but hopefully this will be integrated with the official [llama.cpp](https://github.com/ggerganov/llama.cpp)
|
|
|
|
|
|
|
|
|
17 |
|
18 |
MPT-7B-Instruct is a model for short-form instruction following.
|
19 |
It is built by finetuning [MPT-7B](https://huggingface.co/mosaicml/mpt-7b) on a [dataset](https://huggingface.co/datasets/sam-mosaic/dolly_hhrlhf) derived from the [Databricks Dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) and the [Anthropic Helpful and Harmless (HH-RLHF)](https://huggingface.co/datasets/Anthropic/hh-rlhf) datasets.
|
mpt-7b-instruct-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14707a1f9b20478cac1662a6083fa307a84660ff00dd709da761cb5cf584a3ff
|
3 |
+
size 3912127328
|
mpt-7b-instruct-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77226410cdcf17e803bfb1794cacc1cabea5c11df395fc14be5ea0371c98e906
|
3 |
+
size 7286666080
|