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

[parser] support omegaconf (#7793)

Browse Source
This commit is contained in:
hoshi-hiyouga
2025-04-21 23:30:30 +08:00
committed by GitHub
parent bd7bc31c79
commit 416853dd25
25 changed files with 62 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/merge_lora/llama3_full_sft.yaml
View File

@@ -6,5 +6,5 @@ trust_remote_code: true
### export
export_dir: output/llama3_full_sft
export_size: 5
export_device: cpu
export_device: cpu # choices: [cpu, auto]
export_legacy_format: false

4
examples/merge_lora/llama3_gptq.yaml
View File

@@ -6,7 +6,7 @@ trust_remote_code: true
### export
export_dir: output/llama3_gptq
export_quantization_bit: 4
export_quantization_dataset: data/c4_demo.json
export_quantization_dataset: data/c4_demo.jsonl
export_size: 5
export_device: cpu
export_device: cpu # choices: [cpu, auto]
export_legacy_format: false

2
examples/merge_lora/llama3_lora_sft.yaml
View File

@@ -9,5 +9,5 @@ trust_remote_code: true
### export
export_dir: output/llama3_lora_sft
export_size: 5
export_device: cpu
export_device: cpu # choices: [cpu, auto]
export_legacy_format: false

4
examples/merge_lora/qwen2vl_lora_sft.yaml
View File

@@ -1,7 +1,7 @@
### Note: DO NOT use quantized model or quantization_bit when merging lora adapters
### model
model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
model_name_or_path: Qwen/Qwen2.5-VL-7B-Instruct
adapter_name_or_path: saves/qwen2_vl-7b/lora/sft
template: qwen2_vl
trust_remote_code: true
@@ -9,5 +9,5 @@ trust_remote_code: true
### export
export_dir: output/qwen2_vl_lora_sft
export_size: 5
export_device: cpu
export_device: cpu # choices: [cpu, auto]
export_legacy_format: false