LLM · Text Generation
Llama 3.2 1B OpenHermes 2.5
Instruction-tuned Llama 3.2 1B model fine-tuned on OpenHermes 2.5 dataset for chat and agentic tasks.
About this model
This model is a fine-tuned version of Meta's Llama 3.2 1B, trained on the OpenHermes 2.5 dataset containing 1 million synthetic instruction and chat samples. It features 1.23B parameters, a 128k context window, and supports multilingual text and code generation. The model is intended for assistant-like chat, knowledge retrieval, summarization, and query rewriting tasks. It inherits capabilities and limitations from both the Llama 3.2 1B base model and the OpenHermes 2.5 dataset. Licensed under the Llama 3.2 Community License. Training achieved a final validation loss of 0.8631 after 2.5 epochs.
Project signals
- 33 Hugging Face downloads
- 3 Hugging Face likes
Topics
transformers · pytorch · safetensors · llama · text-generation · fine-tuned · instruction-tuned · dataset:teknium/openhermes-2.5 · base_model:meta-llama/llama-3.2-1b · base_model:finetune:meta-llama/llama-3.2-1b