metadata

base_model: unsloth/SmolLM2-1.7B-Instruct
language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl

Uploaded model

dataset = load_dataset("alexandreteles/AlpacaToxicQA_ShareGPT", split = "train")
dataset2 = load_dataset("Nitral-AI/Active_RP-ShareGPT", split = "train")
dataset3 = load_dataset("Cyleux/skunk-reasoning-29k-sharegpt", split = "train")
dataset4 = load_dataset("isaiahbjork/chain-of-thought-sharegpt", split = "train")
dataset5 = load_dataset("Nitral-AI/Olympiad_Math-ShareGPT", split = "train")
dataset6 = load_dataset("Nitral-AI/RP_Alignment-ShareGPT", split = "train")
dataset7 = load_dataset("MaziyarPanahi/Synthia-Coder-v1.5-I-sharegpt", split = "train")
dataset8 = load_dataset("AiCloser/sharegpt_cot_dataset", split = "train")
dataset9 = load_dataset("Nitral-AI/SciCelQnA_ShareGPT", split = "train")

Developed by: bunnycore
License: apache-2.0
Finetuned from model : unsloth/SmolLM2-1.7B-Instruct

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.