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

Document logits_all

Browse source
This commit is contained in:
oobabooga 2023-11-07 14:45:11 -08:00
parent 5c0559da69
commit 322c170566
2 changed files with 5 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
README.md
View file

@ -327,6 +327,7 @@ Optionally, you can use the following command-line flags:
| `--tensor_split TENSOR_SPLIT` | Split the model across multiple GPUs. Comma-separated list of proportions. Example: 18,17. |
| `--llama_cpp_seed SEED` | Seed for llama-cpp models. Default is 0 (random). |
| `--numa` | Activate NUMA task allocation for llama.cpp. |
| `--logits_all`| Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower. |
| `--cache-capacity CACHE_CAPACITY` | Maximum cache capacity (llama-cpp-python). Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed. |
#### ExLlama