Sara121/Ornith-1.0-9B-Engineering

Ornith-1.0-9B-Engineering

Standalone merged Hugging Face Transformers model created by merging the selected Epoch 2 engineering QLoRA adapter into ornith-ai/Ornith-1.0-9B.

Lineage

ornith-ai/Ornith-1.0-9B + Epoch 2 QLoRA adapter (checkpoint-1072) -> validated standalone merged model.

The original public GGUF model was not used for training or merging.

Training And Selection

• —Training examples: 17,133
• —Frozen evaluation examples: 902
• —Method: QLoRA adapter training, then merge into the full-precision Transformers checkpoint
• —Selected checkpoint: Epoch 2 (checkpoint-1072)

Validation loss:

Epoch 2 was selected because it had the best held-out token F1 and the lowest validation loss. Epoch 3 had one additional exact match, but lower token F1 and higher validation loss.

Frozen Evaluation

All results below use exactly the same frozen 902-example evaluation set.

The merged model was evaluated as a standalone model on all 902 frozen examples.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Sara121/Ornith-1.0-9B-Engineering"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    device_map="auto",
    torch_dtype=torch.bfloat16,
)
model.eval()

Use the bundled tokenizer and chat template. Ornith generation conventions may include <think>...</think> reasoning content before the answer.

Limitations

This is a domain-adapted model for engineering QA and should be validated before use in production or compliance-sensitive workflows. Evaluation metrics are lexical and do not guarantee factual or regulatory correctness.