ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support batch infer in vllm

Browse Source 
Former-commit-id: 3ef5ed3b9a44eed2f7e3ff221dfc343d0a97c0b5
This commit is contained in:
hiyouga
2024-12-04 13:50:00 +00:00
parent 53edd62f8b
commit c1768cfb14
29 changed files with 148 additions and 407 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/inference/llama3.yaml
View File

@@ -1,2 +1,3 @@
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
template: llama3
infer_backend: huggingface # choices: [huggingface, vllm]

1
examples/inference/llama3_lora_sft.yaml
View File

@@ -2,3 +2,4 @@ model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
adapter_name_or_path: saves/llama3-8b/lora/sft
template: llama3
finetuning_type: lora
infer_backend: huggingface # choices: [huggingface, vllm]

1
examples/inference/llava1_5.yaml
View File

@@ -1,2 +1,3 @@
model_name_or_path: llava-hf/llava-1.5-7b-hf
template: llava
infer_backend: huggingface # choices: [huggingface, vllm]

1
examples/inference/qwen2_vl.yaml
View File

@@ -1,2 +1,3 @@
model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
template: qwen2_vl
infer_backend: huggingface # choices: [huggingface, vllm]