Update README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,17 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
library_name: transformers
|
| 9 |
pipeline_tag: text-generation
|
| 10 |
language: en
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
# DAPO RL Checkpoint - Step 0
|
| 13 |
|
|
@@ -58,4 +62,4 @@ prompt = tokenizer.apply_chat_template(
|
|
| 58 |
|
| 59 |
inputs = tokenizer(prompt, return_tensors="pt")
|
| 60 |
outputs = model.generate(**inputs, max_new_tokens=256)
|
| 61 |
-
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
+
- math
|
| 5 |
+
- rl
|
| 6 |
+
- qwen3
|
| 7 |
+
- dapomath17k
|
| 8 |
library_name: transformers
|
| 9 |
pipeline_tag: text-generation
|
| 10 |
language: en
|
| 11 |
+
datasets:
|
| 12 |
+
- BytedTsinghua-SIA/DAPO-Math-17k
|
| 13 |
+
base_model:
|
| 14 |
+
- Qwen/Qwen3-8B-Base
|
| 15 |
---
|
| 16 |
# DAPO RL Checkpoint - Step 0
|
| 17 |
|
|
|
|
| 62 |
|
| 63 |
inputs = tokenizer(prompt, return_tensors="pt")
|
| 64 |
outputs = model.generate(**inputs, max_new_tokens=256)
|
| 65 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|