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

fix: readme

Browse source
This commit is contained in:
Trần Đức Nam 2023-12-22 15:57:25 +07:00
parent 00f48ade6a
commit 9b742c5a52
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
awq-py/README.md
View file

@ -57,7 +57,7 @@ python convert-hf-to-gguf.py models/mpt-7b/ --awq-path awq_cache/llama-7b-w4-g12
# For llama and llama2, and mistral models.
./build/bin/main -m models/llama_7b_q4_0.gguf -n 128 --prompt "Once upon a time"
# For mpt models.
./build/bin/main -m models/mpt_7b_q4_0.gguf -awq -n 128 --prompt "Once upon a time"
./build/bin/main -m models/mpt_7b_q4_0.gguf --use-awq -n 128 --prompt "Once upon a time"
```
## Benchmark
@ -66,7 +66,7 @@ The perplexity measurements in table above are done against the `wikitext2` test
# For llama and llama2, and mistral models.
./perplexity -m models/llama_7b_q4_0.gguf -f datasets/wikitext-2-raw/wiki.test.raw
# For mpt models.
./perplexity -m models/mpt_7b_q4_0.gguf -awq -f datasets/wikitext-2-raw/wiki.test.raw
./perplexity -m models/mpt_7b_q4_0.gguf --use-awq -f datasets/wikitext-2-raw/wiki.test.raw
```
## Results