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

README.md multimodal params fix (#967)

Browse source 
multi modal params fix: add logits = True -> to make llava work
This commit is contained in:
zocainViken 2023-12-12 02:41:38 +01:00 committed by GitHub
parent c1d92ce680
commit 6bbeea07ae
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
README.md
View file

@ -266,7 +266,8 @@ Then you'll need to use a custom chat handler to load the clip model and process
>>> llm = Llama( >>> llm = Llama(
model_path="./path/to/llava/llama-model.gguf", model_path="./path/to/llava/llama-model.gguf",
chat_handler=chat_handler, chat_handler=chat_handler,
n_ctx=2048 # n_ctx should be increased to accomodate the image embedding n_ctx=2048, # n_ctx should be increased to accomodate the image embedding
logits_all=True,# needed to make llava work
) )
>>> llm.create_chat_completion( >>> llm.create_chat_completion(
messages = [ messages = [