|
|
--- |
|
|
license: apache-2.0 |
|
|
datasets: |
|
|
- sequelbox/Celestia3-DeepSeek-R1-0528 |
|
|
base_model: |
|
|
- HuggingFaceTB/SmolLM2-360M-Instruct |
|
|
library_name: transformers |
|
|
language: |
|
|
- en |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- trl |
|
|
- text-generation-inference |
|
|
- r1 |
|
|
- re-think |
|
|
--- |
|
|
|
|
|
 |
|
|
|
|
|
# **SmolLM2-Rethink-360M** |
|
|
|
|
|
> **SmolLM2-Rethink-360M** is an experimental lightweight reasoning model trained on the **Celestia3-DeepSeek-R1-0528** dataset. Built on top of the **SmolLM2-135M-Instruct** architecture and scaled to 360M parameters, it is designed to enhance lightweight reasoning, logical deduction, and structured response generation—all while maintaining efficiency for resource-constrained environments. |
|
|
|
|
|
--- |
|
|
|
|
|
## **Key Highlights** |
|
|
|
|
|
1. **Compact Yet Powerful** |
|
|
With 360M parameters, the model balances performance and efficiency, offering solid reasoning capabilities with fast inference speeds. |
|
|
|
|
|
2. **Reasoning-Oriented Training** |
|
|
Fine-tuned on instruction-tuned datasets like **Celestia3-DeepSeek-R1-0528**, optimized for logical step-by-step thinking. |
|
|
|
|
|
3. **Optimized for Edge & Research** |
|
|
Usable on mid-range GPUs or CPU environments, making it ideal for experimentation, teaching, and lightweight deployment. |
|
|
|
|
|
4. **Structured Generation Support** |
|
|
Capable of outputting well-organized content such as JSON, lists, workflows, and tabular formats. |
|
|
|
|
|
--- |
|
|
|
|
|
## **Quickstart with 🤗 Transformers** |
|
|
|
|
|
```python |
|
|
%%capture |
|
|
!pip install transformers |
|
|
``` |
|
|
|
|
|
```py |
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
|
|
checkpoint = "prithivMLmods/SmolLM2-Rethink-360M" |
|
|
device = "cuda" # or "cpu" |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(checkpoint) |
|
|
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device) |
|
|
|
|
|
messages = [{"role": "user", "content": "What is gravity?"}] |
|
|
input_text = tokenizer.apply_chat_template(messages, tokenize=False) |
|
|
print(input_text) |
|
|
|
|
|
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device) |
|
|
outputs = model.generate( |
|
|
inputs, |
|
|
max_new_tokens=1024, |
|
|
temperature=0.2, |
|
|
top_p=0.9, |
|
|
do_sample=True |
|
|
) |
|
|
|
|
|
print(tokenizer.decode(outputs[0])) |
|
|
``` |
|
|
|
|
|
--- |
|
|
|
|
|
## **Intended Use** |
|
|
|
|
|
* **Lightweight Reasoning Tasks** |
|
|
Suitable for compact agents needing reasoning abilities without high compute requirements. |
|
|
|
|
|
* **Educational & Research Assistants** |
|
|
Ideal for logic tutors, student aides, or research prototypes. |
|
|
|
|
|
* **Instruction Following & Structured QA** |
|
|
Excels in scenarios requiring concise, step-by-step or well-formatted responses. |
|
|
|
|
|
* **Microservices & Embedded AI** |
|
|
Can be embedded in systems with modest hardware, enabling distributed or modular AI. |
|
|
|
|
|
--- |
|
|
|
|
|
## **Limitations** |
|
|
|
|
|
1. **Knowledge Scope** |
|
|
Smaller models naturally have less factual coverage compared to large-scale LLMs. |
|
|
|
|
|
2. **Context Length** |
|
|
Best used with shorter prompts and outputs due to token and memory constraints. |
|
|
|
|
|
3. **Variability in Creative Tasks** |
|
|
Less suited for imaginative writing or nuanced creative expression. |
|
|
|
|
|
4. **Limited Real-World Awareness** |
|
|
Model does not have real-time or post-training data awareness. |
|
|
|
|
|
5. **Prompt Sensitivity** |
|
|
Outputs can vary based on phrasing; best results come from clear, guided prompts. |
