mkurman

A merged model combines the reasoning model's strengths (Qwen2.5-14B-DeepSeek-R1) and the long-context model capabilities (Qwen2.5-14B-Instruct-1M) for versatile performance. and I needed to make some minor adjustments to the tokenizer configuration. You can use it on `LM Studio` or `Ollama` by utilizing the provided GGUF files. License Apache 2.0 for open-source contribution and collaboration.

This model is a variant of o1-like reasoning that has been fine-tuned on MedIT Solutions Llama 3.2 3B Instruct (a variant of Meta LLama 3.2 3B Instruct). The model introduces specific tags (` ` and ` `) for chain-of-thought style text generation, with a focus on instruct-style reasoning tasks. This model was fine-tuned for exact matching rather than generating a diverse distribution. Therefore, I recommend testing it with `dosample=False` or setting `temperature=0.0` for deterministic outputs. Model name: `mkurman/llama-3.2-MEDIT-3B-o1` Type: Small Language Model (SLM) Base model: MedIT Solutions Llama 3.2 3B Instruct (derived from Meta Llama 3.2 3B Instruct) Architecture: 3 billion parameters License: llama3.2 Intended Use Cases: - General question answering - Instruction-based generation - Reasoning and chain-of-thought exploration Not Recommended For: - Sensitive, real-world medical diagnosis without expert verification - Highly domain-specific or regulated fields outside the model’s training scope 1. Stop strings: Because the model uses ` ` and ` ` tags to separate internal reasoning from the final answer, you must supply ` ` as a stop sequence (or multiple stop sequences, if your framework allows) to avoid the model generating infinitely. 2. Preventing ` ` bug: Sometimes the model starts with ` ` instead of the intended ` `. As a workaround, add `" \n\n"` to the end of your generation prompt (in your chat template) to ensure it starts correctly. 3. Libraries/Tools: - Ollama and LM Studio: Via GGUF file. - Jupyter Notebook (or similar): Using the Transformers library. If you are loading the GGUF file, follow the instructions provided by Ollama or LM Studio. Typically, it involves placing the model file in the appropriate directory and selecting it within the interface. You can then issue prompts. Make sure to set stop sequences to ` ` (and possibly ` ` if your environment supports multiple stops). In a Jupyter Notebook or Python Script (Transformers) Note: If your generation library does not allow direct stop sequences, you can manually parse and remove any tokens that appear after ` `. (Remember to add ` \n\n` at the end if you see the ` ` bug.) You would display the ` ` portion as the final user-facing answer. - Hallucination: The model may generate plausible-sounding but incorrect or nonsensical answers. - Medical Information: Never rely on this model as a source of truth! this model is not a certified medical professional. Always verify with qualified experts before acting on medical advice. - Biases: The model’s outputs may reflect biases present in the training data. Users should evaluate content for fairness and accuracy. Please refer to the base model’s Llama 3.2 Community License Agreement and any additional licenses from MedIT Solutions. If you use this model in your work, please cite: For questions, comments, or issues related to `mkurman/llama-3.2-MEDIT-3B-o1`, please open an issue on the model repository or contact mkurman.

- Developed by: mkurman - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.