phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-08 13:00:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

drop custom classes to manage hydra

Browse source
This commit is contained in:
Hardik Shah 2024-07-22 20:40:50 -07:00
parent 86fff23a9e
commit aca6bfe0df
4 changed files with 17 additions and 82 deletions
Download patch file Download diff file Expand all files Collapse all files

17
llama_toolchain/data/default_inference_config.yaml
View file

@ -1,9 +1,14 @@
inference_config:
impl_type: "inline"
inline_config:
checkpoint_type: "pytorch"
checkpoint_dir: {checkpoint_dir}/
tokenizer_path: {checkpoint_dir}/tokenizer.model
model_parallel_size: {model_parallel_size}
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: 2048
max_batch_size: 1