Instructions to use pszemraj/rnj-1.5-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pszemraj/rnj-1.5-instruct with Transformers:

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

pipe = pipeline("text-generation", model="pszemraj/rnj-1.5-instruct")
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("pszemraj/rnj-1.5-instruct")
model = AutoModelForCausalLM.from_pretrained("pszemraj/rnj-1.5-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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pszemraj/rnj-1.5-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pszemraj/rnj-1.5-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": "pszemraj/rnj-1.5-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pszemraj/rnj-1.5-instruct

SGLang

How to use pszemraj/rnj-1.5-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 "pszemraj/rnj-1.5-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": "pszemraj/rnj-1.5-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 "pszemraj/rnj-1.5-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": "pszemraj/rnj-1.5-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pszemraj/rnj-1.5-instruct with Docker Model Runner:
```
docker model run hf.co/pszemraj/rnj-1.5-instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

rnj-1.5-instruct (sliding-window patched)

Drop-in transformers repack of EssentialAI/rnj-1.5-instruct intended for quick inference tests, downstream software compatiblity (transformers/torch itself, llama.cpp, etc):

Upstream declares layer_types: chunked_attention, which modeling_gemma3.py doesn't implement - inference crashes with KeyError: 'chunked_attention'. This repo swaps those entries to sliding_attention so the model loads under stock transformers. Weights unchanged, resaved in bf16.

Sliding window (8192) is not identical to the original block-local attention - equivalent for prompts ~< 8192 tokens, divergent beyond that. For faithful long-context inference, use vLLM 0.20.0 against the upstream repo.

Changes vs upstream

Field	Upstream	Here
Local layer type	chunked_attention	sliding_attention
RoPE params for locals	under chunked_attention key	moved to sliding_attention key
Dtype	float32	bfloat16
Architecture string	Rnj1ForCausalLM	Gemma3ForCausalLM

Local/global layer pattern (LLLGLLLGLLLGLGGGGGLGLLLGLLLGLLLL) preserved.

Usage

import torch
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="pszemraj/rnj-1.5-instruct",
    dtype=torch.bfloat16,
    device_map="auto",
)
res = pipe([{"role": "user", "content": "Who are you?"}])
print(res)

License

Apache 2.0, inherited from upstream. See the original model card for architecture, benchmarks, and citation.

Downloads last month: 22

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for pszemraj/rnj-1.5-instruct

Base model

EssentialAI/rnj-1

Finetuned

(8)

this model

Quantizations

1 model