SmolLM2 135M Constitutional ChitChat v1 is a fine tuned conversational language model built on the SmolLM2 135M Instruct base model. The model was fine tuned using the Chitchat Constitutional AI dataset with QLoRA to improve conversational quality empathy and instruction following while maintaining a lightweight footprint. The model is intended for friendly conversations casual dialogue emotional support style interactions and general conversational assistance. After fine tuning the model was merged with the base model converted to GGUF format and validated for local inference using llama cpp. Key Features Lightweight 135M parameter model Fine tuned using Constitutional AI ChitChat dataset QLoRA based parameter efficient fine tuning GGUF compatible Suitable for local CPU and GPU inference Optimized for conversational AI Limitations The model is not intended for factual question answering advanced reasoning mathematical problem solving or coding assistance. It may generate inaccurate factual information and should not be used for high risk applications requiring guaranteed correctness.
Apache 2.0
Governance and Administration
Shlok Pankaj Salunke
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
Open
27/06/26 14:41:18
N.A.
229.67 MB
© 2026 - Copyright AIKosh. All rights reserved.