vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

convert-new.py : output gguf (#2635)

Browse source 
* convert-new.py : output gguf (WIP)

* convert-new.py : add gguf key-value pairs

* llama : add hparams.ctx_train + no longer print ftype

* convert-new.py : minor fixes

* convert-new.py : vocab-only option should work now

* llama : fix tokenizer to use llama_char_to_byte

* tests : add new ggml-vocab-llama.gguf

* convert-new.py : tensor name mapping

* convert-new.py : add map for skipping tensor serialization

* convert-new.py : convert script now works

* gguf.py : pick some of the refactoring from #2644

* convert-new.py : minor fixes
This commit is contained in:
Georgi Gerganov 2023-08-17 17:19:52 +03:00 • committed by GitHub
parent d6fd53afd6
commit e0429d38e4
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
9 changed files with 526 additions and 327 deletions
Download patch file Download diff file Expand all files Collapse all files

2
convert-llama-7b-pth-to-gguf.py
View file

@ -298,7 +298,7 @@ for part_name in part_names:
print( name + ", shape " + str(len(data.shape)) + ", " + str(old_dtype) + " --> " + str(data.dtype))
gguf_writer.write_tensor_to_file(data)
gguf_writer.write_tensor_data(data)
gguf_writer.close()