mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Implement CFG for ExLlama_HF (#3666)

Browse source
This commit is contained in:
oobabooga 2023-08-24 16:27:36 -03:00 • committed by GitHub
parent 2b675533f7
commit d6934bc7bc
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 122 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

1
README.md
View file

@ -304,6 +304,7 @@ Optionally, you can use the following command-line flags:
|------------------|-------------|
|`--gpu-split` | Comma-separated list of VRAM (in GB) to use per GPU device for model layers, e.g. `20,7,7` |
|`--max_seq_len MAX_SEQ_LEN` | Maximum sequence length. |
|`--cfg-cache` | ExLlama_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader, but not necessary for CFG with base ExLlama. |
#### GPTQ-for-LLaMa