llama.cpp
SimpleChat Completion Mode flexibility and cleanup, Settings gMe, Optional sliding window
#7480
Merged
Merged
SimpleChat Completion Mode flexibility and cleanup, Settings gMe, Optional sliding window #7480
mofosyne
merged
19 commits into
ggml-org:master
from
hanishkvc:hkvc_webfrontend_simplechat_v2
hanishkvc
changed the title
SimpleChat: A placeholder system prompt, Use usage msg in code
8042cb95
SimpleChat:CompletionMode: Allow control of Role: prefix
3c11098d
SimpleChat:Completion: Avoid Role: prefix; Newline only in between
0dba8f88
SimpleChat:CompletionMode: Update readme/usage, trim textarea newline
7a0a4236
SimpleChat:SC: Ensure proper clearing/reseting
fe60655e
SimpleChat: Update usage note and readme a bit
01594dae
SimpleChat:Completion: clear any prev chat history at begining
e2164d66
SimpleChat:Try read json early, if available
40fbbeb2
SimpleChat: Rename the half asleep mis-spelled global var
5d84a92d
SimpleChat: Common chat request options from a global object
073eae67
SimpleChat: Update title, usage and readme a bit
59f74c7d
SimpleChat:ChatRequestOptions: max_tokens
cbd853ed
SimpleChat: Reduce max_tokens to be small but still sufficient
4b29736d
SimpleChat: Consolidate global vars into gMe, Display to user
f0dd91d5
SimpleChat:SlidingWindow: iRecentUserMsgCnt to limit context load
b57aad79
SimpleChat: placeholder based usage hint for user-in textarea
11d2d316
SimpleChat: Try make user experience better, if possible
8f172b90
SimpleChat:Add n_predict (equiv max_tokens) for llamacpp server
b3afd6c8
mofosyne
approved these changes
on 2024-05-25
SimpleChat: Note about trying to keep things simple yet flexible
6d2f3d9d
mofosyne
approved these changes
on 2024-05-26
Reviewers
Assignees
No one assigned
Labels
examples
Review Complexity : Low
server
merge ready
Milestone
No milestone
Login to write a write a comment.
Login via GitHub