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

Remove RWKV loader (#5130)

Browse source
This commit is contained in:
oobabooga 2023-12-31 02:01:40 -03:00 • committed by GitHub
parent 0e54a09bcb
commit 2734ce3e4c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 3 additions and 189 deletions
Download patch file Download diff file Expand all files Collapse all files

7
README.md
View file

@ -312,13 +312,6 @@ List of command-line flags
| `--nvme-offload-dir NVME_OFFLOAD_DIR` | DeepSpeed: Directory to use for ZeRO-3 NVME offloading. |
| `--local_rank LOCAL_RANK` | DeepSpeed: Optional argument for distributed setups. |
#### RWKV
| Flag | Description |
|---------------------------------|-------------|
| `--rwkv-strategy RWKV_STRATEGY` | RWKV: The strategy to use while loading the model. Examples: "cpu fp32", "cuda fp16", "cuda fp16i8". |
| `--rwkv-cuda-on` | RWKV: Compile the CUDA kernel for better performance. |
#### RoPE (for llama.cpp, ExLlamaV2, and transformers)
| Flag | Description |