Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

Commit 6bbeea0

Browse filesBrowse files
zocainVikenzocainViken
authored
README.md multimodal params fix (abetlen#967)
multi modal params fix: add logits = True -> to make llava work
1 parent c1d92ce commit 6bbeea0
Copy full SHA for 6bbeea0

File tree

Expand file treeCollapse file tree

1 file changed

+2
-1
lines changed
Filter options
Expand file treeCollapse file tree

1 file changed

+2
-1
lines changed

‎README.md

Copy file name to clipboardExpand all lines: README.md
+2-1Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -266,7 +266,8 @@ Then you'll need to use a custom chat handler to load the clip model and process
266266
>>> llm = Llama(
267267
model_path="./path/to/llava/llama-model.gguf",
268268
chat_handler=chat_handler,
269-
n_ctx=2048 # n_ctx should be increased to accomodate the image embedding
269+
n_ctx=2048, # n_ctx should be increased to accomodate the image embedding
270+
logits_all=True,# needed to make llava work
270271
)
271272
>>> llm.create_chat_completion(
272273
messages = [

0 commit comments

Comments
0 (0)
Morty Proxy This is a proxified and sanitized view of the page, visit original site.