Instructions to use EssentialAI/rnj-1-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EssentialAI/rnj-1-instruct with Transformers:

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

pipe = pipeline("text-generation", model="EssentialAI/rnj-1-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EssentialAI/rnj-1-instruct")
model = AutoModelForCausalLM.from_pretrained("EssentialAI/rnj-1-instruct")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use EssentialAI/rnj-1-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EssentialAI/rnj-1-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": "EssentialAI/rnj-1-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EssentialAI/rnj-1-instruct

SGLang

How to use EssentialAI/rnj-1-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 "EssentialAI/rnj-1-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": "EssentialAI/rnj-1-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 "EssentialAI/rnj-1-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": "EssentialAI/rnj-1-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EssentialAI/rnj-1-instruct with Docker Model Runner:
```
docker model run hf.co/EssentialAI/rnj-1-instruct
```

Research-EAI commited on Dec 18, 2025

Commit

f2c7da2

verified ·

1 Parent(s): 75d870a

Changelog for update to Rnj-1.

Browse files

Files changed (1) hide show

README.md +18 -2

README.md CHANGED Viewed

@@ -1,6 +1,8 @@
 ---
 license: apache-2.0
 library_name: transformers
 ---
 # Rnj-1
@@ -66,6 +68,16 @@ library_name: transformers
 Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models. These models perform well across a range of programming languages and boast strong agentic capabilities (e.g., inside agentic frameworks like mini-SWE-agent), while also excelling at tool-calling. They additionally exhibit strong capabilities in math and science. Herein, `rnj-1` refers to the base model, while `rnj-1-instruct` refers to the post-trained instruction tuned model.
 # Capabilities
 We evaluate Rnj-1 models against models of comparable size. In addition to accuracy, we also show the FLOPs used in pre-training for each model.
@@ -159,9 +171,13 @@ The global batch sizes used were:
 # Recommendations
-### Temperature
-We recommend using temperatures in the range [0, 0.6] for `rnj-1-instruct`.
 ### Propensity to write code

 ---
 license: apache-2.0
 library_name: transformers
+base_model:
+- EssentialAI/rnj-1
 ---
 # Rnj-1
 Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models. These models perform well across a range of programming languages and boast strong agentic capabilities (e.g., inside agentic frameworks like mini-SWE-agent), while also excelling at tool-calling. They additionally exhibit strong capabilities in math and science. Herein, `rnj-1` refers to the base model, while `rnj-1-instruct` refers to the post-trained instruction tuned model.
+# Changelog
+* Update December 18, 2025:
+  - System prompt and temperature recommendations: Resolve premature truncations and mitigate unprompted code outputs.
+  - Updates to default chat template.
+  - Updated STEM and comparables tables.
+  - Links to model generations for evals.
+* Initial version: December 8, 2025
 # Capabilities
 We evaluate Rnj-1 models against models of comparable size. In addition to accuracy, we also show the FLOPs used in pre-training for each model.
 # Recommendations
+### System Prompt & Temperature
+We recommend _always_ adding a system prompt. `You are a helpful assistant.` is a good default prompt to use.
+We recommend using temperatures in the range [0, 0.2] for `rnj-1-instruct`.
+Failure to follow these recommendations can result in a) truncated outputs, b) code outputs even for non-code prompts.
 ### Propensity to write code