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

common : remote --random-prompt usages

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-06-03 17:09:23 +03:00
parent 4bb93223dd
commit b47e91ed75
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
4 changed files with 10 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

10
examples/gguf-split/tests.sh
View file

@ -41,7 +41,7 @@ echo PASS
echo echo
# 2b. Test the sharded model is loading properly # 2b. Test the sharded model is loading properly
$MAIN --model $WORK_PATH/ggml-model-split-00001-of-00006.gguf --random-prompt --n-predict 32 $MAIN --model $WORK_PATH/ggml-model-split-00001-of-00006.gguf --n-predict 32
echo PASS echo PASS
echo echo
@ -51,7 +51,7 @@ echo PASS
echo echo
# 3b. Test the merged model is loading properly # 3b. Test the merged model is loading properly
$MAIN --model $WORK_PATH/ggml-model-merge.gguf --random-prompt --n-predict 32 $MAIN --model $WORK_PATH/ggml-model-merge.gguf --n-predict 32
echo PASS echo PASS
echo echo
@ -61,7 +61,7 @@ echo PASS
echo echo
# 4b. Test the sharded model is loading properly # 4b. Test the sharded model is loading properly
$MAIN --model $WORK_PATH/ggml-model-split-32-tensors-00001-of-00007.gguf --random-prompt --n-predict 32 $MAIN --model $WORK_PATH/ggml-model-split-32-tensors-00001-of-00007.gguf --n-predict 32
echo PASS echo PASS
echo echo
@ -71,7 +71,7 @@ echo
#echo #echo
# 5b. Test the merged model is loading properly # 5b. Test the merged model is loading properly
#$MAIN --model $WORK_PATH/ggml-model-merge-2.gguf --random-prompt --n-predict 32 #$MAIN --model $WORK_PATH/ggml-model-merge-2.gguf --n-predict 32
#echo PASS #echo PASS
#echo #echo
@ -81,7 +81,7 @@ echo PASS
echo echo
# 6b. Test the sharded model is loading properly # 6b. Test the sharded model is loading properly
$MAIN --model $WORK_PATH/ggml-model-split-2G-00001-of-00002.gguf --random-prompt --n-predict 32 $MAIN --model $WORK_PATH/ggml-model-split-2G-00001-of-00002.gguf --n-predict 32
echo PASS echo PASS
echo echo

5
examples/main/README.md
View file

@ -53,13 +53,13 @@ The following command generates "infinite" text from a starting prompt (you can
#### Unix-based systems (Linux, macOS, etc.): #### Unix-based systems (Linux, macOS, etc.):
```bash ```bash
./main -m models/7B/ggml-model.bin --ignore-eos -n -1 --random-prompt ./main -m models/7B/ggml-model.bin --ignore-eos -n -1
``` ```
#### Windows: #### Windows:
```powershell ```powershell
main.exe -m models\7B\ggml-model.bin --ignore-eos -n -1 --random-prompt main.exe -m models\7B\ggml-model.bin --ignore-eos -n -1
``` ```
## Common Options ## Common Options
@ -80,7 +80,6 @@ The `main` program provides several ways to interact with the LLaMA models using
- `--prompt PROMPT`: Provide a prompt directly as a command-line option. - `--prompt PROMPT`: Provide a prompt directly as a command-line option.
- `--file FNAME`: Provide a file containing a prompt or multiple prompts. - `--file FNAME`: Provide a file containing a prompt or multiple prompts.
- `--interactive-first`: Run the program in interactive mode and wait for input right away. (More on this below.) - `--interactive-first`: Run the program in interactive mode and wait for input right away. (More on this below.)
- `--random-prompt`: Start with a randomized prompt.
## Interaction ## Interaction

4
examples/quantize/tests.sh
View file

@ -47,7 +47,7 @@ echo PASS
echo echo
# 3a. Test the requanted model is loading properly # 3a. Test the requanted model is loading properly
$MAIN --model $WORK_PATH/ggml-model-requant-00001-of-00006.gguf --random-prompt --n-predict 32 $MAIN --model $WORK_PATH/ggml-model-requant-00001-of-00006.gguf --n-predict 32
echo PASS echo PASS
echo echo
@ -57,7 +57,7 @@ echo PASS
echo echo
# 4b. Test the requanted model is loading properly # 4b. Test the requanted model is loading properly
$MAIN --model $WORK_PATH/ggml-model-requant-merge.gguf --random-prompt --n-predict 32 $MAIN --model $WORK_PATH/ggml-model-requant-merge.gguf --n-predict 32
echo PASS echo PASS
echo echo

2
scripts/run-with-preset.py
View file

@ -18,7 +18,7 @@ CLI_ARGS_MAIN_PERPLEXITY = [
"low-vram", "main-gpu", "memory-f32", "mirostat", "mirostat-ent", "mirostat-lr", "mlock", "low-vram", "main-gpu", "memory-f32", "mirostat", "mirostat-ent", "mirostat-lr", "mlock",
"model", "multiline-input", "n-gpu-layers", "n-predict", "no-mmap", "no-mul-mat-q", "model", "multiline-input", "n-gpu-layers", "n-predict", "no-mmap", "no-mul-mat-q",
"np-penalize-nl", "numa", "ppl-output-type", "ppl-stride", "presence-penalty", "prompt", "np-penalize-nl", "numa", "ppl-output-type", "ppl-stride", "presence-penalty", "prompt",
"prompt-cache", "prompt-cache-all", "prompt-cache-ro", "random-prompt", "repeat-last-n", "prompt-cache", "prompt-cache-all", "prompt-cache-ro", "repeat-last-n",
"repeat-penalty", "reverse-prompt", "rope-freq-base", "rope-freq-scale", "rope-scale", "seed", "repeat-penalty", "reverse-prompt", "rope-freq-base", "rope-freq-scale", "rope-scale", "seed",
"simple-io", "tensor-split", "threads", "temp", "tfs", "top-k", "top-p", "typical", "simple-io", "tensor-split", "threads", "temp", "tfs", "top-k", "top-p", "typical",
"verbose-prompt" "verbose-prompt"