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

Add CFG to llamacpp_HF (second attempt) (#3678)

Browse source
This commit is contained in:
oobabooga 2023-08-24 20:32:21 -03:00 • committed by GitHub
parent d6934bc7bc
commit 3320accfdc
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 14 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

1
README.md
View file

@ -280,6 +280,7 @@ Optionally, you can use the following command-line flags:
| `--n_gqa N_GQA` | grouped-query attention. Must be 8 for llama-2 70b. |
| `--rms_norm_eps RMS_NORM_EPS` | 5e-6 is a good value for llama-2 models. |
| `--cpu` | Use the CPU version of llama-cpp-python instead of the GPU-accelerated version. |
|`--cfg-cache` | llamacpp_HF: Create an additional cache for CFG negative prompts. |
#### ctransformers