Instructions to use InterstellarCG/HRM-Text-1B-Code-FT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InterstellarCG/HRM-Text-1B-Code-FT with Transformers:

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

pipe = pipeline("text-generation", model="InterstellarCG/HRM-Text-1B-Code-FT")

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

tokenizer = AutoTokenizer.from_pretrained("InterstellarCG/HRM-Text-1B-Code-FT")
model = AutoModelForCausalLM.from_pretrained("InterstellarCG/HRM-Text-1B-Code-FT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use InterstellarCG/HRM-Text-1B-Code-FT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InterstellarCG/HRM-Text-1B-Code-FT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InterstellarCG/HRM-Text-1B-Code-FT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/InterstellarCG/HRM-Text-1B-Code-FT

SGLang

How to use InterstellarCG/HRM-Text-1B-Code-FT 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 "InterstellarCG/HRM-Text-1B-Code-FT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InterstellarCG/HRM-Text-1B-Code-FT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "InterstellarCG/HRM-Text-1B-Code-FT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InterstellarCG/HRM-Text-1B-Code-FT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use InterstellarCG/HRM-Text-1B-Code-FT with Docker Model Runner:
```
docker model run hf.co/InterstellarCG/HRM-Text-1B-Code-FT
```

HRM-Text-1B Code Fine-tuned

Fine-tuned from HRM-Text-1B on combined code dataset (192M tokens).

Training Details

Base: HRM-Text-1B (stacked from HTML/CSS 100k checkpoint)
Dataset: Combined code (Python, JavaScript, TypeScript, SQL, HTML/CSS)
Tokens: 192M
Epochs: 3
Learning rate: 1e-5

Capabilities

Python code generation
JavaScript functions
SQL queries
General QA (improved over base)

Limitations

Weak at React/TSX syntax
HTML/CSS output can be malformed
TypeScript interfaces not well-formed

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("InterstellarCG/HRM-Text-1B-Code-FT")
tokenizer = AutoTokenizer.from_pretrained("InterstellarCG/HRM-Text-1B-Code-FT")

Evaluation

Task	Base	Fine-tuned
Python (is_prime)	Garbage	Correct
JS (reverse array)	Garbage	Correct
SQL (join query)	Garbage	Correct
QA (Paris capital)	Garbage	Correct

Downloads last month: 12

Safetensors

Model size

1B params

Tensor type

BF16