Update README.md
Browse files
README.md
CHANGED
@@ -12,14 +12,14 @@ base_model:
|
|
12 |
- Qwen/Qwen2.5-Coder-1.5B-Instruct
|
13 |
---
|
14 |
|
15 |
-
# VeriReason-Qwen2.5-1.
|
16 |
|
17 |
For implementation details, visit our GitHub repository: [VeriReason](https://github.com/NellyW8/VeriReason)
|
18 |
|
19 |
Check out our paper: [VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation](https://arxiv.org/abs/2505.11849)
|
20 |
|
21 |
## Update Log
|
22 |
-
2025.05.17: Initial release of VeriReason-Qwen2.5-1.
|
23 |
|
24 |
## Project Description
|
25 |
|
@@ -42,7 +42,7 @@ You can use the model with the transformers library:
|
|
42 |
import torch
|
43 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
44 |
|
45 |
-
model_name = "Nellyw888/VeriReason-Qwen2.5-1.
|
46 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
47 |
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
|
48 |
model.eval()
|
|
|
12 |
- Qwen/Qwen2.5-Coder-1.5B-Instruct
|
13 |
---
|
14 |
|
15 |
+
# VeriReason-Qwen2.5-1.5b-RTLCoder-Verilog-GRPO-reasoning-tb
|
16 |
|
17 |
For implementation details, visit our GitHub repository: [VeriReason](https://github.com/NellyW8/VeriReason)
|
18 |
|
19 |
Check out our paper: [VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation](https://arxiv.org/abs/2505.11849)
|
20 |
|
21 |
## Update Log
|
22 |
+
2025.05.17: Initial release of VeriReason-Qwen2.5-1.5b-RTLCoder-Verilog-GRPO-reasoning-tb
|
23 |
|
24 |
## Project Description
|
25 |
|
|
|
42 |
import torch
|
43 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
44 |
|
45 |
+
model_name = "Nellyw888/VeriReason-Qwen2.5-1.5b-RTLCoder-Verilog-GRPO-reasoning-tb"
|
46 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
47 |
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
|
48 |
model.eval()
|