Instructions to use dappalumbo91/FSOT-Qwen2.5-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dappalumbo91/FSOT-Qwen2.5-7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="dappalumbo91/FSOT-Qwen2.5-7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dappalumbo91/FSOT-Qwen2.5-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("dappalumbo91/FSOT-Qwen2.5-7B-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dappalumbo91/FSOT-Qwen2.5-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dappalumbo91/FSOT-Qwen2.5-7B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dappalumbo91/FSOT-Qwen2.5-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dappalumbo91/FSOT-Qwen2.5-7B-Instruct

SGLang

How to use dappalumbo91/FSOT-Qwen2.5-7B-Instruct 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 "dappalumbo91/FSOT-Qwen2.5-7B-Instruct" \
    --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": "dappalumbo91/FSOT-Qwen2.5-7B-Instruct",
		"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 "dappalumbo91/FSOT-Qwen2.5-7B-Instruct" \
        --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": "dappalumbo91/FSOT-Qwen2.5-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dappalumbo91/FSOT-Qwen2.5-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/dappalumbo91/FSOT-Qwen2.5-7B-Instruct
```

FSOT-Qwen2.5-7B-Instruct

Conversational mouth for Fluid Spacetime Omni-Theory (FSOT) Monte Carlo Intelligence.


Base	Qwen/Qwen2.5-7B-Instruct
Role	Articulate docs/tissue RAG + live fold scalars — not a new law engine
Law court	Pin D1D38A · `free_parameters = 0` · FSOT-2.1-Lean
Code	FSOT-Monte-Carlo-Intelligence

Important

FSOT = Fluid Spacetime Omni-Theory (Damian Arthur Palumbo).
Seeds / (K) / pin are never trained by this product.
Optional LoRA adapters for articulation live in the code repo under data/models/articulation/lora/ (local); this HF repo hosts the base safetensors.
Soft court promote ≠ Lean-proved. Green gate ≤0.5% ≠ multipath map occupancy.

Use with the product

git clone https://github.com/dappalumbo91/FSOT-Monte-Carlo-Intelligence.git
cd FSOT-Monte-Carlo-Intelligence
pip install -e ".[narrate]"
python scripts/download_qwen25_instruct.py
python -m fsot_mc serve --port 8765
# UI: 2D/3D toggle · Talk to the work (this model) · free_parameters=0

Product UI includes 2D + 3D connective graph (As Above So Below shells) and docs RAG chat over this base model (+ optional local LoRA adapters, not in this HF repo).