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

Remove GGML support

Browse source
This commit is contained in:
oobabooga 2023-09-11 07:30:56 -07:00
parent cc7b7ba153
commit ed86878f02
15 changed files with 24 additions and 123 deletions
Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -158,7 +158,7 @@ text-generation-webui
│   │   └── tokenizer.model
```
* GGML/GGUF models are a single file and should be placed directly into `models`. Example:
* GGUF models are a single file and should be placed directly into `models`. Example:
```
text-generation-webui
@ -260,7 +260,7 @@ Optionally, you can use the following command-line flags:
| `--quant_type QUANT_TYPE` | quant_type for 4-bit. Valid options: nf4, fp4. |
| `--use_double_quant` | use_double_quant for 4-bit. |
#### GGML/GGUF (for llama.cpp and ctransformers)
#### GGUF (for llama.cpp and ctransformers)
| Flag | Description |
|-------------|-------------|
@ -279,8 +279,6 @@ Optionally, you can use the following command-line flags:
| `--cache-capacity CACHE_CAPACITY` | Maximum cache capacity. Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed. |
| `--tensor_split TENSOR_SPLIT` | Split the model across multiple GPUs, comma-separated list of proportions, e.g. 18,17 |
| `--llama_cpp_seed SEED` | Seed for llama-cpp models. Default 0 (random). |
| `--n_gqa N_GQA` | GGML only (not used by GGUF): Grouped-Query Attention. Must be 8 for llama-2 70b. |
| `--rms_norm_eps RMS_NORM_EPS` | GGML only (not used by GGUF): 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. |