Upload folder using huggingface_hub

.gitattributes

@@ -32,4 +32,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+mpt-7b-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+mpt-7b-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 mpt-7b-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -11,15 +11,9 @@ inference: false
 
 # MPT-7B-Instruct
 
-<span style="color:red">This is not working yet with the official version of llama.cpp</span>
-
 This is the GGUF version of MPT-7B-Instruct based on [jploski's fork of llama.cpp](https://github.com/jploski/llama.cpp)
 
-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)
-
-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)
-
------
+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)
 
 MPT-7B-Instruct is a model for short-form instruction following.
 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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14707a1f9b20478cac1662a6083fa307a84660ff00dd709da761cb5cf584a3ff
+size 3912127328

mpt-7b-instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77226410cdcf17e803bfb1794cacc1cabea5c11df395fc14be5ea0371c98e906
+size 7286666080