PR for metadata overrride merged to llama.cpp . Update repo to match

.gitmodules

@@ -3,7 +3,7 @@
 	url = https://huggingface.co/Maykeye/TinyLLama-v0
 [submodule "llama.cpp"]
 	path = llama.cpp
-	url = [email protected]:mofosyne/llama.cpp.git
+	url = [email protected]:ggerganov/llama.cpp.git
 [submodule "llamafile"]
 	path = llamafile
 	url = [email protected]:Mozilla-Ocho/llamafile.git

README.md

@@ -58,7 +58,7 @@ llamafile is a new format introduced by Mozilla Ocho on Nov 20th 2023. It uses C
 
 * You have already pulled in all the submodules including Maykeye's model in safe.tensor format
 * Your git has LFS configured correctly or you get this issue https://github.com/ggerganov/llama.cpp/issues/1994 where `safe.tensor` doesn't download properly (and only a small pointer file is downloaded)
-* You are using llama.cpp repo that has some extra changes to convert.py to support metadata import (for now it's pointed to my repo. A [Pull Request is Pending at the main llama.cpp for this feature](https://github.com/ggerganov/llama.cpp/pull/4858))
+* Within llama.cpp repo we already merged a [PR](https://github.com/ggerganov/llama.cpp/pull/4858) for some changes to convert.py to support metadata override (to add some missing authorship information)
 
 ## Replication Steps
 

TinyLLama-v0-5M-F16.llamafile

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6fee85a6906722ef26d7f8925485654220ac3870d56ec1b8e260919e2dc33a4
-size 19468831
+oid sha256:65f4dec0c5d74d643abd288c33bed2ef34fe7a8edfa2df1d725c4fbd63678b61
+size 18560827

llama.cpp

@@ -1 +1 @@
-Subproject commit 74fe2ea7a8d713da7378812215213ba74050cda6
+Subproject commit b1f8af1886e8187db6bb2a9b87cfc1c0f175f629

llamafile

@@ -1 +1 @@
-Subproject commit 790029485fdd3a81284efdcae1c0483a4d39a6a6
+Subproject commit d4099feff737f3be9a4bed017f1315a4d2cb773a

maykeye_tinyllama-metadata.json

@@ -5,6 +5,6 @@
     "general.url": "https://huggingface.co/mofosyne/TinyLLama-v0-llamafile",
     "general.description": "This gguf is ported from a first version of Maykeye attempt at recreating roneneldan/TinyStories-1M but using Llama architecture",
     "general.license": "apache-2.0",
-    "general.source_url": "https://huggingface.co/Maykeye/TinyLLama-v0",
-    "general.source_hf_repo": "https://huggingface.co/Maykeye/TinyLLama-v0"
+    "general.source.url": "https://huggingface.co/Maykeye/TinyLLama-v0",
+    "general.source.huggingface.repository": "https://huggingface.co/Maykeye/TinyLLama-v0"
 }