Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,16 @@ tags:
|
|
| 10 |
- qwen3
|
| 11 |
- atomight
|
| 12 |
- atomightv2-5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
<div align="center">
|
|
@@ -120,4 +130,8 @@ messages = [
|
|
| 120 |
|
| 121 |
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
|
| 122 |
outputs = model.generate(inputs, max_new_tokens=512)
|
| 123 |
-
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
- qwen3
|
| 11 |
- atomight
|
| 12 |
- atomightv2-5
|
| 13 |
+
datasets:
|
| 14 |
+
- Logics-MLLM/Logics-STEM-SFT-Dataset-Open-1.6M
|
| 15 |
+
- MegaScience/MegaScience
|
| 16 |
+
- nvidia/OpenMathReasoning
|
| 17 |
+
- zwhe99/DeepMath-103K
|
| 18 |
+
- trl-lib/DeepMath-103K
|
| 19 |
+
- nvidia/OpenCodeInstruct
|
| 20 |
+
- nvidia/Nemotron-SFT-Competitive-Programming-v2
|
| 21 |
+
base_model:
|
| 22 |
+
- Qwen/Qwen3-1.7B
|
| 23 |
---
|
| 24 |
|
| 25 |
<div align="center">
|
|
|
|
| 130 |
|
| 131 |
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
|
| 132 |
outputs = model.generate(inputs, max_new_tokens=512)
|
| 133 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
| 134 |
+
|
| 135 |
+
```
|
| 136 |
+
|
| 137 |
+
This model is a fine-tuned derivative of Qwen3-1.7B (Apache 2.0) and is released under CC-BY-4.0 in accordance with the licenses of its training datasets. If you use this model, please credit `NovatasticRoScript/Atomight-V2.5-1.7B` and the base model/datasets listed above. Part of the Atomight family — small models, curated data, no shortcuts.
|