Stop works while reading; newer llama.cpp (b11514)
Browse files- GRAFT-Code.exe +2 -2
- README.md +1 -0
GRAFT-Code.exe
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd1ac7ef431efad2203d816337ff4c04487a8c371e16be5977f89931497a392a
|
| 3 |
+
size 43979595
|
README.md
CHANGED
|
@@ -62,6 +62,7 @@ the folder from the sidebar.
|
|
| 62 |
- *Agent:* max steps, command timeout, auto-approve and full access.
|
| 63 |
- **Chat history.** Every chat is saved in the sidebar. Reopen one and GRAFT remembers it.
|
| 64 |
- **Copy, Regenerate and a context gauge** that shows how much of GRAFT's memory the chat uses.
|
|
|
|
| 65 |
- **Speculative decoding.** If a matching draft model (`GRAFT-10B-A2B-draft-*.gguf`) sits next to GRAFT-10B-A2B,
|
| 66 |
GRAFT Code uses it automatically for faster replies.
|
| 67 |
- **Use the model from other apps.** While GRAFT Code is open, its model is also an OpenAI-compatible API at
|
|
|
|
| 62 |
- *Agent:* max steps, command timeout, auto-approve and full access.
|
| 63 |
- **Chat history.** Every chat is saved in the sidebar. Reopen one and GRAFT remembers it.
|
| 64 |
- **Copy, Regenerate and a context gauge** that shows how much of GRAFT's memory the chat uses.
|
| 65 |
+
- **Stop anytime**, even while GRAFT is still reading a long message, not just while it writes.
|
| 66 |
- **Speculative decoding.** If a matching draft model (`GRAFT-10B-A2B-draft-*.gguf`) sits next to GRAFT-10B-A2B,
|
| 67 |
GRAFT Code uses it automatically for faster replies.
|
| 68 |
- **Use the model from other apps.** While GRAFT Code is open, its model is also an OpenAI-compatible API at
|