Instructions to use hyperspaceai/thor-1-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hyperspaceai/thor-1-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-35B-A3B")
model = PeftModel.from_pretrained(base_model, "hyperspaceai/thor-1-lora")

Transformers

How to use hyperspaceai/thor-1-lora with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="hyperspaceai/thor-1-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("hyperspaceai/thor-1-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hyperspaceai/thor-1-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hyperspaceai/thor-1-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hyperspaceai/thor-1-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hyperspaceai/thor-1-lora

SGLang

How to use hyperspaceai/thor-1-lora with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "hyperspaceai/thor-1-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hyperspaceai/thor-1-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "hyperspaceai/thor-1-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hyperspaceai/thor-1-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hyperspaceai/thor-1-lora with Docker Model Runner:
```
docker model run hf.co/hyperspaceai/thor-1-lora
```

THOR-1: Unified MoE Brain

THOR-1 is a LoRA adapter for Qwen3.5-35B-A3B (MoE: 35B total params, 3B active) that unifies 6 AI orchestration capabilities into a single model.

Capabilities (6 modes)

Mode	Tag	Purpose
Intent	`[INTENT]`	Classify user intent and extract parameters
Decompose	`[DECOMPOSE]`	Break complex tasks into executable DAG steps
Execute	`[EXECUTE]`	Iterative REPL-style code execution
Predict	`[PREDICT]`	Predict execution outcomes (world model)
Route	`[ROUTE]`	Route inference across providers/models
Rank	`[RANK]`	Rank and select agents/skills/tools

Each training example has a mode tag prefix in the system prompt that teaches the model to activate different expert mixtures per task type.

Training Details

Base model: Qwen3.5-35B-A3B (hybrid linear attention + Mamba SSM + 256 MoE experts)
Method: LoRA (r=16, alpha=32, targets: q_proj + v_proj)
Training data: 6,384 examples across 6 modes (SFT format)
Epochs: 3 (1,077 steps)
Best validation loss: 0.2504
Training time: 12.9 hours on NVIDIA H100 80GB
Precision: BF16 with BitsAndBytes 4-bit quantization (NF4)
Optimizer: AdamW 8-bit, LR=2e-5 with cosine decay

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-35B-A3B", trust_remote_code=True)
model = PeftModel.from_pretrained(base_model, "hyperspaceai/thor-1-lora")
tokenizer = AutoTokenizer.from_pretrained("hyperspaceai/thor-1-lora")

prompt = "<|im_start|>system\n[INTENT] Classify the user's intent.\n<|im_end|>\n<|im_start|>user\nBook a flight to Tokyo next Friday<|im_end|>\n<|im_start|>assistant\n"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Part of the Thor Ecosystem

THOR-1 is the unified brain of the Thor AI orchestration system, powering intelligent task routing, agent selection, and execution planning across 21 named agents and 1,200+ community agents.

Developed by: HyperspaceAI

Downloads last month: -

Model tree for hyperspaceai/thor-1-lora

Base model

Qwen/Qwen3.5-35B-A3B-Base

Finetuned

Qwen/Qwen3.5-35B-A3B

Adapter

(24)

this model