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

Merge 4f8d62e444 into 326b418b59

Browse source
This commit is contained in:
akawrykow 2024-01-12 00:46:53 -06:00 • committed by GitHub
commit 3a8e6d07c3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -601,7 +601,8 @@ Building the program with BLAS support may lead to some performance improvements
```bash ```bash
# obtain the original LLaMA model weights and place them in ./models # obtain the original LLaMA model weights and place them in ./models
ls ./models ls ./models
65B 30B 13B 7B tokenizer_checklist.chk tokenizer.model 65B 30B 13B 7B tokenizer.model
# [Optional] for models using BPE tokenizers # [Optional] for models using BPE tokenizers
ls ./models ls ./models
65B 30B 13B 7B vocab.json 65B 30B 13B 7B vocab.json
@ -610,7 +611,8 @@ ls ./models
python3 -m pip install -r requirements.txt python3 -m pip install -r requirements.txt
# convert the 7B model to ggml FP16 format # convert the 7B model to ggml FP16 format
python3 convert.py models/7B/ # Use --ctx 4096 for LLaMA v2
python3 convert.py models/7B/ --ctx 2048
# [Optional] for models using BPE tokenizers # [Optional] for models using BPE tokenizers
python convert.py models/7B/ --vocabtype bpe python convert.py models/7B/ --vocabtype bpe