vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

readme : update default prompt context size

Browse source
This commit is contained in:
Nikolaos Pothitos 2024-11-12 22:44:44 +00:00
parent 905b990be0
commit 1e421ec1ac
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/infill/README.md
View file

@ -14,7 +14,7 @@ In this section, we cover the most commonly used options for running the `infill
- `-m FNAME, --model FNAME`: Specify the path to the LLaMA model file (e.g., `models/7B/ggml-model.bin`). - `-m FNAME, --model FNAME`: Specify the path to the LLaMA model file (e.g., `models/7B/ggml-model.bin`).
- `-i, --interactive`: Run the program in interactive mode, allowing you to provide input directly and receive real-time responses. - `-i, --interactive`: Run the program in interactive mode, allowing you to provide input directly and receive real-time responses.
- `-n N, --n-predict N`: Set the number of tokens to predict when generating text. Adjusting this value can influence the length of the generated text. - `-n N, --n-predict N`: Set the number of tokens to predict when generating text. Adjusting this value can influence the length of the generated text.
- `-c N, --ctx-size N`: Set the size of the prompt context. The default is 512, but LLaMA models were built with a context of 2048, which will provide better results for longer input/inference. - `-c N, --ctx-size N`: Set the size of the prompt context. The default is 4096, but if a LLaMA model was built with a longer context, increasing this value will provide better results for longer input/inference.
- `--spm-infill`: Use Suffix/Prefix/Middle pattern for infill (instead of Prefix/Suffix/Middle) as some models prefer this. - `--spm-infill`: Use Suffix/Prefix/Middle pattern for infill (instead of Prefix/Suffix/Middle) as some models prefer this.
## Input Prompts ## Input Prompts

4
examples/main/README.md
View file

@ -66,7 +66,7 @@ In this section, we cover the most commonly used options for running the `llama-
- `-mu MODEL_URL --model-url MODEL_URL`: Specify a remote http url to download the file (e.g [https://huggingface.co/ggml-org/gemma-1.1-7b-it-Q4_K_M-GGUF/resolve/main/gemma-1.1-7b-it.Q4_K_M.gguf?download=true](https://huggingface.co/ggml-org/gemma-1.1-7b-it-Q4_K_M-GGUF/resolve/main/gemma-1.1-7b-it.Q4_K_M.gguf?download=true)). - `-mu MODEL_URL --model-url MODEL_URL`: Specify a remote http url to download the file (e.g [https://huggingface.co/ggml-org/gemma-1.1-7b-it-Q4_K_M-GGUF/resolve/main/gemma-1.1-7b-it.Q4_K_M.gguf?download=true](https://huggingface.co/ggml-org/gemma-1.1-7b-it-Q4_K_M-GGUF/resolve/main/gemma-1.1-7b-it.Q4_K_M.gguf?download=true)).
- `-i, --interactive`: Run the program in interactive mode, allowing you to provide input directly and receive real-time responses. - `-i, --interactive`: Run the program in interactive mode, allowing you to provide input directly and receive real-time responses.
- `-n N, --n-predict N`: Set the number of tokens to predict when generating text. Adjusting this value can influence the length of the generated text. - `-n N, --n-predict N`: Set the number of tokens to predict when generating text. Adjusting this value can influence the length of the generated text.
- `-c N, --ctx-size N`: Set the size of the prompt context. The default is 512, but LLaMA models were built with a context of 2048, which will provide better results for longer input/inference. - `-c N, --ctx-size N`: Set the size of the prompt context. The default is 4096, but if a LLaMA model was built with a longer context, increasing this value will provide better results for longer input/inference.
- `-mli, --multiline-input`: Allows you to write or paste multiple lines without ending each in '\' - `-mli, --multiline-input`: Allows you to write or paste multiple lines without ending each in '\'
- `-t N, --threads N`: Set the number of threads to use during generation. For optimal performance, it is recommended to set this value to the number of physical CPU cores your system has. - `-t N, --threads N`: Set the number of threads to use during generation. For optimal performance, it is recommended to set this value to the number of physical CPU cores your system has.
- `-ngl N, --n-gpu-layers N`: When compiled with GPU support, this option allows offloading some layers to the GPU for computation. Generally results in increased performance. - `-ngl N, --n-gpu-layers N`: When compiled with GPU support, this option allows offloading some layers to the GPU for computation. Generally results in increased performance.
@ -131,7 +131,7 @@ During text generation, LLaMA models have a limited context size, which means th
### Context Size ### Context Size
- `-c N, --ctx-size N`: Set the size of the prompt context (default: 0, 0 = loaded from model). The LLaMA models were built with a context of 2048-8192, which will yield the best results on longer input/inference. - `-c N, --ctx-size N`: Set the size of the prompt context (default: 4096, 0 = loaded from model). If a LLaMA model was built with a longer context, increasing this value will yield the best results on longer input/inference.
### Extended Context Size ### Extended Context Size