phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-16 18:08:09 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Initial commit

Browse source
This commit is contained in:
Ashwin Bharambe 2024-06-25 15:47:57 -07:00 • committed by Ashwin Bharambe
commit 5d5acc8ed5
81 changed files with 4458 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_toolchain/data/default_inference_config.yaml Normal file
View file

@ -0,0 +1,14 @@
inference_config:
impl_config:
impl_type: "inline"
checkpoint_config:
checkpoint:
checkpoint_type: "pytorch"
checkpoint_dir: {checkpoint_dir}/
tokenizer_path: {checkpoint_dir}/tokenizer.model
model_parallel_size: {model_parallel_size}
quantization_format: bf16
quantization: null
torch_seed: null
max_seq_len: 16384
max_batch_size: 1