Kiel-2.2-Sol

Kiel-2.2-Sol is a high-performance multi-domain instruction model. It is engineered to excel in complex logical reasoning, advanced coding patterns (such as asynchronous Python workflows), and multi-domain problem solving. As part of the KielTech ecosystem, it serves as the core text intelligence engine powering responsive chat interfaces and backend generative pipelines.

Model Details

• Developed by: KielTech
• Model Type: Causal Language Model (Fully Merged Standalone Weights)
• Base Model: kiel2/Kiel-2.1-Sol
• Language(s): English
• Format: Safetensors (FP16 optimized for high-throughput cloud serving)
• Hugging Face Hub: kiel2/Kiel-2.2-Sol

Model Sources

• Repository: Hugging Face Hub
• Ecosystem: Kiel AI Suite (Integrated with KielForge and Kiel-2-OCR/VQA suites)

Uses

Direct Use

• Advanced conversational AI assistants and chat sidebars.
• Automated code generation, asynchronous programming helpers, and software architecture reasoning.
• Multi-domain task execution requiring strict instruction-following.

Downstream Use

• Can be deployed as a primary standalone language model backend for commercial APIs using high-throughput serving engines like vLLM and Text Generation Inference (TGI).

How to Get Started with the Model

Because Kiel-2.2-Sol is provided as a fully merged standalone model in safetensors format, you can load and run it directly without any PEFT wrapper dependencies:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL_ID = "kiel2/Kiel-2.2-Sol"

print(f"Loading {MODEL_ID} tokenizer and model...")
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
if tokenizer.pad_token is None:
    tokenizer.pad_token = tokenizer.eos_token

model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True
)
model.eval()

# Test prompt
prompt = (
    "System: You are Kiel-2.2-Sol, an advanced multi-domain AI assistant.\n"
    "User: Write a robust Python function using asyncio and aiohttp to concurrently fetch JSON payloads."
)

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512, ## you can adjust this
        temperature=0.7,
        top_p=0.9,
        do_sample=True,
        pad_token_id=tokenizer.eos_token_id
    )

response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(response)
Citation
Code snippet
@misc{kiel2-Kiel-2.2-Sol-2026,
  author = {KielTech},
  title = {Kiel-2.2-Sol: High-Performance Multi-Domain Language Model},
  year = {2026},
  publisher = {Hugging Face},
  journal = {Hugging Face Repository},
  howpublished = {\url{[https://huggingface.co/kiel2/Kiel-2.2-Sol](https://huggingface.co/kiel2/Kiel-2.2-Sol)}}
}