Text Generation
Safetensors
English
qwen2
causal-lm
grpo
reasoning
reinforcement-learning
mini-llm
text-generation-inference
lm-evaluation-harness
conversational
Eval Results (legacy)
Instructions to use NovatasticRoScript/Atomight-V2.1-0.5B-Inference with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Inference
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,17 +5,18 @@ tags:
|
|
| 5 |
- transformers
|
| 6 |
- unsloth
|
| 7 |
- qwen2
|
| 8 |
-
license:
|
| 9 |
language:
|
| 10 |
- en
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
-
# Uploaded finetuned
|
| 14 |
|
| 15 |
- **Developed by:** NovatasticRoScript
|
| 16 |
-
- **License:**
|
| 17 |
- **Finetuned from model :** unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit
|
| 18 |
|
| 19 |
-
This
|
| 20 |
|
| 21 |
-
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
| 5 |
- transformers
|
| 6 |
- unsloth
|
| 7 |
- qwen2
|
| 8 |
+
license: mit
|
| 9 |
language:
|
| 10 |
- en
|
| 11 |
+
new_version: NovatasticRoScript/Atomight-2-1.5B-Thinking
|
| 12 |
---
|
| 13 |
|
| 14 |
+
# Uploaded finetuned model
|
| 15 |
|
| 16 |
- **Developed by:** NovatasticRoScript
|
| 17 |
+
- **License:** mit
|
| 18 |
- **Finetuned from model :** unsloth/qwen2.5-0.5b-instruct-unsloth-bnb-4bit
|
| 19 |
|
| 20 |
+
This model was trained 2x faster with [Unsloth] and Huggingface's TRL library.
|
| 21 |
|
| 22 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|