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

Various ctransformers fixes (#3556)

Browse source 
---------

Co-authored-by: cal066 <cal066@users.noreply.github.com>
This commit is contained in:
Eve 2023-08-13 22:09:03 -04:00 • committed by GitHub
parent b8df4a436e
commit 66c04c304d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 33 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

19
README.md
View file

@ -205,7 +205,7 @@ Optionally, you can use the following command-line flags:
| Flag | Description |
|--------------------------------------------|-------------|
| `--loader LOADER` | Choose the model loader manually, otherwise, it will get autodetected. Valid options: transformers, autogptq, gptq-for-llama, exllama, exllama_hf, llamacpp, rwkv |
| `--loader LOADER` | Choose the model loader manually, otherwise, it will get autodetected. Valid options: transformers, autogptq, gptq-for-llama, exllama, exllama_hf, llamacpp, rwkv, ctransformers |
#### Accelerate/transformers
@ -235,22 +235,33 @@ 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. |
#### llama.cpp
#### GGML (for llama.cpp and ctransformers)
| Flag | Description |
|-------------|-------------|
| `--threads` | Number of threads to use. |
| `--n_batch` | Maximum number of prompt tokens to batch together when calling llama_eval. |
| `--n-gpu-layers N_GPU_LAYERS` | Number of layers to offload to the GPU. Only works if llama-cpp-python was compiled with BLAS. Set this to 1000000000 to offload all layers to the GPU. |
| `--n_ctx N_CTX` | Size of the prompt context. |
#### llama.cpp
| Flag | Description |
|-------------|-------------|
| `--no-mmap` | Prevent mmap from being used. |
| `--mlock` | Force the system to keep the model in RAM. |
| `--cache-capacity CACHE_CAPACITY` | Maximum cache capacity. Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed. |
| `--n-gpu-layers N_GPU_LAYERS` | Number of layers to offload to the GPU. Only works if llama-cpp-python was compiled with BLAS. Set this to 1000000000 to offload all layers to the GPU. |
| `--n_ctx N_CTX` | Size of the prompt context. |
| `--llama_cpp_seed SEED` | Seed for llama-cpp models. Default 0 (random). |
| `--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. |
#### ctransformers
| Flag | Description |
|-------------|-------------|
| `--model_type MODEL_TYPE` | Model type of pre-quantized model. Currently gpt2, gptj, gpt_neox, falcon, llama, mpt, gpt_bigcode, dolly-v2, and replit are supported. |
#### AutoGPTQ
| Flag | Description |