Text Generation
Transformers
Safetensors
English
Portuguese
multilingual
qwen3_5
image-text-to-text
rein
rein-npc
typed-decision
decision-model
tool-calling
roleplay
game-npc
soft-prompt
qwen3.5
llama.cpp
conversational
Instructions to use jmc0/Rein-NPC-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jmc0/Rein-NPC-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jmc0/Rein-NPC-4B") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("jmc0/Rein-NPC-4B") model = AutoModelForMultimodalLM.from_pretrained("jmc0/Rein-NPC-4B", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jmc0/Rein-NPC-4B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jmc0/Rein-NPC-4B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jmc0/Rein-NPC-4B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/jmc0/Rein-NPC-4B
- SGLang
How to use jmc0/Rein-NPC-4B 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 "jmc0/Rein-NPC-4B" \ --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": "jmc0/Rein-NPC-4B", "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 "jmc0/Rein-NPC-4B" \ --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": "jmc0/Rein-NPC-4B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use jmc0/Rein-NPC-4B with Docker Model Runner:
docker model run hf.co/jmc0/Rein-NPC-4B
Download examples/decide.json from jmc0/Rein-NPC-4B: direct link, hf CLI and curl.
- Browser
- Download file 2.52 kB
-
https://huggingface.co/jmc0/Rein-NPC-4B/resolve/main/examples/decide.json
- Command line
-
hf download hf://jmc0/Rein-NPC-4B/examples/decide.json
-
curl -L -o decide.json https://huggingface.co/jmc0/Rein-NPC-4B/resolve/main/examples/decide.json
2.52 kB
| { | |
| "prompt": "<|fim_prefix|>Context:\nI am Mira Ashgrove, keeper of the Ashgrove General Store in the frontier town of Thornwall. I have run this shop for twenty years and I know every farmer, hunter and wanderer who comes through the door. My tone is brisk and friendly, with a dry joke now and then; I haggle a little but my prices are fair and I say so. I sell gear and supplies, I buy what travelers bring back from the hills, and I repair armor and weapons at the bench in the back. In my world, every sale is written into Thornwall's ledger the moment coin changes hands, and no sale can be undone. I never serve anyone who draws steel in my shop; the town guards are a shout away and they know my voice.\n\nLate afternoon, rain on the roof. The bell over the door rings as a traveler steps in, dripping. Current state: { \"gold_in_till\": 320, \"stock\": { \"iron sword\": 2, \"healing potion\": 5, \"rope (50 ft)\": 10, \"lantern oil\": 8 }, \"guards_nearby\": true }\nConversation:\n<|im_start|>user\nAfternoon! Rough road out there. What have you got for sale?<|im_end|>\n<|fim_middle|><|rein_0|><|rein_1|><|rein_2|><|rein_3|><|rein_4|><|rein_5|><|rein_6|><|rein_7|><|rein_8|><|rein_9|><|rein_10|><|rein_11|><|rein_12|><|rein_13|><|rein_14|><|rein_15|><|rein_16|><|rein_17|><|rein_18|><|rein_19|><|rein_20|><|rein_21|><|rein_22|><|rein_23|><|rein_24|><|rein_25|><|rein_26|><|rein_27|><|rein_28|><|rein_29|><|rein_30|><|rein_31|><|rein_32|><|rein_33|><|rein_34|><|rein_35|><|rein_36|><|rein_37|><|rein_38|><|rein_39|><|rein_40|><|rein_41|><|rein_42|><|rein_43|><|rein_44|><|rein_45|><|rein_46|><|rein_47|>Should Mira Ashgrove use one of her tools now, because the customer asks for it or because the situation calls for it, and which one?<|box_start|>A. show_inventory: the customer wants to know what is for sale or how much something costs<|box_start|>B. sell_item: the customer decides to buy something from the stock<|box_start|>C. buy_item: the customer offers to sell Mira something<|box_start|>D. repair_gear: the customer wants a piece of equipment fixed<|box_start|>E. call_guards: someone threatens Mira, draws a weapon, or tries to rob the store<|box_start|>F. none: talk, questions, stories, or requests her tools cannot serve<|rein_48|><|rein_49|><|rein_50|><|rein_51|><|rein_52|><|rein_53|><|rein_54|><|rein_55|><|rein_56|><|rein_57|><|rein_58|><|rein_59|><|rein_60|><|rein_61|><|rein_62|><|rein_63|><|fim_suffix|>", | |
| "n_predict": 1, | |
| "n_probs": 60, | |
| "temperature": 0.0, | |
| "cache_prompt": true | |
| } | |