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

Revert "Bump llama-cpp-python to 0.2.18 (#4611)"

Browse source 
This reverts commit 923c8e25fb.
This commit is contained in:
oobabooga 2023-11-17 05:14:25 -08:00
parent e0a7cc5e0f
commit 9d6f79db74
17 changed files with 174 additions and 92 deletions
Download patch file Download diff file Expand all files Collapse all files

1
README.md
View file

@ -325,6 +325,7 @@ Optionally, you can use the following command-line flags:
| `--mlock` | Force the system to keep the model in RAM. |
| `--n-gpu-layers N_GPU_LAYERS` | Number of layers to offload to the GPU. |
| `--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. |