Instructions to use jasoncarreira/hrm-text-code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jasoncarreira/hrm-text-code with Transformers:

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

pipe = pipeline("text-generation", model="jasoncarreira/hrm-text-code")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jasoncarreira/hrm-text-code")
model = AutoModelForCausalLM.from_pretrained("jasoncarreira/hrm-text-code", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jasoncarreira/hrm-text-code with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jasoncarreira/hrm-text-code

SGLang

How to use jasoncarreira/hrm-text-code 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 "jasoncarreira/hrm-text-code" \
    --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": "jasoncarreira/hrm-text-code",
		"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 "jasoncarreira/hrm-text-code" \
        --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": "jasoncarreira/hrm-text-code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jasoncarreira/hrm-text-code with Docker Model Runner:
```
docker model run hf.co/jasoncarreira/hrm-text-code
```

Combining code & tool calling in a single model?

by vonjack - opened 6 days ago

Discussion

vonjack

6 days ago

•

edited 6 days ago

Hey! Really enjoying both hrm-text-code and hrm-text-agent-v2.

I was thinking—since writing code and calling tools both rely on pretty similar logic (structured output formats, precise syntax, step-by-step reasoning), have you considered training a model that combines both using DFM Mimir's method?

A single model that handles coding while seamlessly triggering function/tool calls would be amazing for local agent workflows. Curious if this is on your radar or if blending those datasets introduces too much task interference!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment