🚀 Pixtral 12B Fine-Tuned on Titan-Hohmann-Transfer-Orbit

✨ Updated tomistralai/Pixtral-12B-Base-2409.

🌟 Overview

Fine-tuned variant of Pixtral 12B for orbital mechanics with emphasis on Hohmann transfer orbits. Supports multimodal (image + text) inputs and text outputs.

🔧 Model Details

• Base: mistralai/Pixtral-12B-Base-2409
• Type: 🖼️ Multimodal (Vision + Text)
• Params: ~12B (decoder) + vision encoder
• Languages: 🇺🇸 English
• License: 📄 MIT

🎯 Intended Use

• 🛰️ Hohmann transfer ∆v estimation
• ⏱️ Transfer-time approximations
• 🔍 Orbit analysis aids and reasoning

🚀 Quickstart

🌐 vLLM (multimodal)

from vllm import LLM
from vllm.sampling_params import SamplingParams

llm = LLM(model="mistralai/Pixtral-12B-Base-2409", tokenizer_mode="mistral")
sampling = SamplingParams(max_tokens=512, temperature=0.2)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Given this diagram, estimate the delta-v for a Hohmann transfer to Titan."},
            {"type": "image_url", "image_url": {"url": "https://example.com/orbit_diagram.png"}}
        ]
    }
]
resp = llm.chat(messages, sampling_params=sampling)
print(resp[0].outputs[0].text)

🤗 Transformers (text-only demo)

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "mistralai/Pixtral-12B-Base-2409"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

prompt = "Compute approximate delta-v for a Hohmann transfer to Titan. State assumptions."
inputs = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512, temperature=0.2)
print(tok.decode(out[0], skip_special_tokens=True))

📊 Training Data

• Dataset: Taylor658/titan-hohmann-transfer-orbit
• Modalities: 📝 text (explanations), 💻 code (snippets), 🖼️ images (orbital diagrams)

⚠️ Limitations

• 🎯 Optimized for Hohmann transfers and related reasoning
• 💾 Requires sufficient GPU VRAM for best throughput

🙏 Acknowledgements

• Base model by Mistral AI (Pixtral 12B)
• Dataset by A Taylor

📞 Contact Information

• Author: 👨‍🚀 A Taylor
• Email: 📧
• Repository: 🔗 https://github.com/ATaylorAerospace/HohmannHET

---