vivekvar
/

GSPO-DeepSeek-R1-Distill-Qwen-1.5B

Text Generation

reinforcement-learning

mathematical-reasoning

policy-optimization

sequence-level-training

Model card Files Files and versions Community

vivekvar commited on 21 days ago

Commit

3840067

·

verified ·

1 Parent(s): afe6a9d

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -57,7 +57,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 # Load the model
-model_name = "your-username/gspo-reasoning-model"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)

 import torch
 # Load the model
+model_name = "vivekvar/GSPO-DeepSeek-R1-Distill-Qwen-1.5B"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)