Instructions to use Shadow0482/tb-x1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Shadow0482/tb-x1 with Transformers:

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

pipe = pipeline("text-generation", model="Shadow0482/tb-x1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Shadow0482/tb-x1")
model = AutoModelForCausalLM.from_pretrained("Shadow0482/tb-x1", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Shadow0482/tb-x1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Shadow0482/tb-x1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Shadow0482/tb-x1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Shadow0482/tb-x1

SGLang

How to use Shadow0482/tb-x1 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 "Shadow0482/tb-x1" \
    --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": "Shadow0482/tb-x1",
		"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 "Shadow0482/tb-x1" \
        --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": "Shadow0482/tb-x1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Shadow0482/tb-x1 with Docker Model Runner:
```
docker model run hf.co/Shadow0482/tb-x1
```

tb-x1 / README.md

Shadow0482

Update README.md

8bd52c4 verified 7 days ago

preview code

Raw History Blame Contribute Delete

3.91 kB

metadata

base_model: orangejuicesmith/Mythos-Nano-safetensor
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - qwen2
  - agentic-workflows
  - tool-calling
license: apache-2.0
language:
  - en

TB-X1 — Mythos Nano

TB-X1 is a model release in the TB-X series, developed by Shadow0482, based on Mythos Nano.

The model is distributed in Safetensors format and is intended for use with the Hugging Face Transformers ecosystem.

Model Information

Property	Details
Model	TB-X1
Developer	Shadow0482
Base model	Mythos Nano
Architecture	Qwen2
Model format	Safetensors
Framework	Hugging Face Transformers
Optimization	Unsloth
Language	English
License	Apache 2.0

Development Methodology

TB-X1 was developed using a teacher-guided, tool-driven agent workflow.

Teacher Models

Claude Opus 5.5 — Teacher model for instruction and response generation.
GPT-6 Astra — Teacher model for reasoning and workflow support.

Agent Orchestration

The development workflow incorporates:

Multi-step agent interactions.
Tool-call orchestration.
Teacher-guided instruction generation.
Structured reasoning workflows.
Model evaluation and refinement.

Approximately 500 million tool-call and agent-flow interactions were used throughout the reported development workflow.

This figure represents workflow activity, not model parameters, training tokens, or dataset samples.

Model Format

TB-X1 uses the Safetensors format.

Benefits include:

Compatibility with Hugging Face Transformers.
Efficient model weight loading.
Support for GPU and CPU inference, depending on model architecture and hardware.
Integration with fine-tuning and model optimization workflows.

Usage

Installation

pip install -U transformers torch accelerate safetensors

Load with Transformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "Shadow0482/tb-x1"

tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True
)

messages = [
    {"role": "user", "content": "Hello! Introduce yourself."}
]

inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

outputs = model.generate(
    inputs,
    max_new_tokens=256,
    temperature=0.7,
    do_sample=True
)

print(tokenizer.decode(
    outputs[0][inputs.shape[-1]:],
    skip_special_tokens=True
))

Hugging Face Pipeline

from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="Shadow0482/tb-x1",
    device_map="auto"
)

result = pipe(
    "Explain how AI agents work.",
    max_new_tokens=256
)

print(result[0]["generated_text"])

Compatibility

Designed for the Hugging Face ecosystem:

Transformers
Safetensors
Text Generation Inference (TGI)
PyTorch
Accelerate
Unsloth-compatible workflows

Actual compatibility depends on the model architecture, configuration, and runtime version.

Acknowledgements

Base model: orangejuicesmith/Mythos-Nano-safetensor
Optimization framework: Unsloth
Teacher models: Claude Opus 5.5 and GPT-6 Astra
Model ecosystem: Hugging Face Transformers

License

The base model metadata specifies the Apache 2.0 license. Please review the original model repository and applicable license terms before redistribution.

TB-X Series

Developed and maintained by Shadow0482.