Text Generation
PEFT
Safetensors
English
Spanish
llama4_text
agriculture
climate
crop-calendar
evidence-grounding
bilingual
lora
autoscientist
adaption
conversational
4-bit precision
bitsandbytes
Instructions to use MarianaCodebase/AgroVeritas-Scout-17B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use MarianaCodebase/AgroVeritas-Scout-17B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("togethercomputer/Llama-4-Scout-17B-16E-Instruct_bnb_4bit") model = PeftModel.from_pretrained(base_model, "MarianaCodebase/AgroVeritas-Scout-17B") - Notebooks
- Google Colab
- Kaggle
| { | |
| "release_model_id": "adaption_llama_4_scout_17b_16_agri_evidence_qa_158a7fd8", | |
| "category": "Agriculture", | |
| "evaluation_source": "Adaption AutoScientist held-out Agriculture category tasks", | |
| "base_win_rate_percent": 23, | |
| "adapted_win_rate_percent": 78, | |
| "absolute_improvement_percentage_points": 55, | |
| "relative_lift_percent": 239.1, | |
| "adapted_to_base_ratio": 3.391, | |
| "training": { | |
| "global_steps": 159, | |
| "epochs": 3, | |
| "first_recorded_eval_loss": 0.756591796875, | |
| "final_eval_loss": 0.682373046875 | |
| }, | |
| "data_quality": { | |
| "same_run_score_before": 9.0, | |
| "same_run_score_after": 10.0, | |
| "same_run_relative_improvement_percent": 11.1, | |
| "grade_before": "A", | |
| "grade_after": "A", | |
| "percentile_before": 43.9, | |
| "percentile_after": 57.7 | |
| }, | |
| "claim_boundaries": [ | |
| "The held-out evaluator prompts are private and are not published.", | |
| "The C-to-A result is a cross-version project development journey, not a same-run quality comparison.", | |
| "The model release is the 158a7fd8 run; the 2329bca3 retry is excluded." | |
| ] | |
| } | |