obscura/minimind
1
0
Fork 0
mirror of https://github.com/jingyaogong/minimind.git synced 2026-09-25 12:27:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: align LoRA inference paths with training output

Browse Source
This commit is contained in:
Daoyuan Li
2026-09-21 23:24:55 -07:00
parent 1e6e909f88
commit 4b86522f8a
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
eval_llm.py
+1 -1
View File
@@ -23,7 +23,7 @@ def init_model(args):
model.load_state_dict(torch.load(ckp, map_location=args.device), strict=True)
if args.lora_weight != 'None':
apply_lora(model)
load_lora(model, f'./{args.save_dir}/{args.lora_weight}_{args.hidden_size}.pth')
load_lora(model, f'./{args.save_dir}/{args.lora_weight}_{args.hidden_size}{moe_suffix}.pth')
else:
model = AutoModelForCausalLM.from_pretrained(args.load_from, trust_remote_code=True)
get_model_params(model, model.config)
scripts/serve_openai_api.py
+1 -1
View File
@@ -40,7 +40,7 @@ def init_model(args):
model.load_state_dict(torch.load(ckp, map_location=device), strict=True)
if args.lora_weight != 'None':
apply_lora(model)
load_lora(model, f'../{args.save_dir}/lora/{args.lora_weight}_{args.hidden_size}.pth')
load_lora(model, f'../{args.save_dir}/{args.lora_weight}_{args.hidden_size}{moe_suffix}.pth')
else:
model = AutoModelForCausalLM.from_pretrained(args.load_from, trust_remote_code=True)
print(f'MiniMind模型参数量: {sum(p.numel() for p in model.parameters()) / 1e6:.2f} M(illion)')