localNFchatbot

localNFchatbot is the CopyleftCultivars local natural-farming chatbot model.

This repository contains the v5 clean merged model checkpoint, promoted from the local training run documented in autoresearch/configs/v5-clean-baseline.yaml in the source project.

Model details

• Base model: Qwen/Qwen3-0.6B
• Training/merge source: local LoRA adapter outputs/lora-adapter-p6-lr5e5-r2
• Uploaded checkpoint: outputs/merged-model-p6-lr5e5-r2
• Merge dtype: float16
• Format: Hugging Face Transformers checkpoint with safetensors

Intended use

Text generation for natural-farming, soil, compost, natural fertilizer, and agroecology chatbot experiments.

Loading example

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "CopyleftCultivars/localNFchatbot"

tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(repo_id, device_map="auto")

messages = [
    {"role": "user", "content": "How can I make a simple natural fertilizer for seedlings?"},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.6, top_p=0.95, do_sample=True)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Notes

This is an experimental fine-tuned local model. Validate recommendations against local ecological context and safety requirements before applying them in the field.