Instructions to use deepconradlabs/conrad-nit-5.1-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepconradlabs/conrad-nit-5.1-8B with Transformers:

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

pipe = pipeline("text-generation", model="deepconradlabs/conrad-nit-5.1-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepconradlabs/conrad-nit-5.1-8B")
model = AutoModelForCausalLM.from_pretrained("deepconradlabs/conrad-nit-5.1-8B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepconradlabs/conrad-nit-5.1-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepconradlabs/conrad-nit-5.1-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepconradlabs/conrad-nit-5.1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepconradlabs/conrad-nit-5.1-8B

SGLang

How to use deepconradlabs/conrad-nit-5.1-8B 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 "deepconradlabs/conrad-nit-5.1-8B" \
    --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": "deepconradlabs/conrad-nit-5.1-8B",
		"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 "deepconradlabs/conrad-nit-5.1-8B" \
        --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": "deepconradlabs/conrad-nit-5.1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepconradlabs/conrad-nit-5.1-8B with Docker Model Runner:
```
docker model run hf.co/deepconradlabs/conrad-nit-5.1-8B
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

CONRAD NIT 5.1 (8B) — Overview

Conrad NIT 5.1 is an instruction-tuned multilingual language model designed for text generation and conversational use cases.

It supports chat-style interaction, reasoning tasks, summarization, code generation, and general natural language processing workflows.

The model is compatible with the Hugging Face Transformers ecosystem and standard text-generation pipelines.

Model Details Model type: Decoder-only transformer Architecture: Llama-compatible 8B parameter class Framework: PyTorch / Transformers Primary task: Text generation Input: Text Output: Text Supported Languages English German French Italian Portuguese Hindi Spanish Thai Intended Use

Conrad NIT 5.1 is intended for:

Conversational assistants Question answering systems Content generation Summarization tasks Code generation support Multilingual applications Out-of-Scope Use

The model is not intended for:

Legal, medical, or financial advice without review Autonomous decision-making in high-risk systems Surveillance or identity tracking Illegal or harmful applications How to Use (Transformers) from transformers import pipeline

model_id = "deepconradlabs/conrad-nit-5.1-8B"

pipe = pipeline( "text-generation", model=model_id )

messages = [ {"role": "user", "content": "Explain quantum computing in simple terms"} ]

output = pipe(messages, max_new_tokens=200) print(output[0]["generated_text"]) Alternative Usage (Auto Model) from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "deepconradlabs/conrad-nit-5.1-8B"

tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id)

prompt = "Write a short explanation of AI models." inputs = tokenizer(prompt, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=200)

print(tokenizer.decode(outputs[0], skip_special_tokens=True)) Model Behavior

The model is optimized for:

Instruction following Multilingual coherence Balanced creativity and factual responses Structured outputs when prompted

Limitations may include:

Hallucinations in ambiguous prompts Reduced accuracy in niche domains Variation in long-context reasoning Safety

Users should implement:

Output filtering Human-in-the-loop review for critical systems Retrieval augmentation for factual accuracy Application-level guardrails Technical Notes Architecture: Llama-compatible transformer decoder Tokenizer: Hugging Face compatible tokenizer Context length: dependent on runtime configuration Precision: bf16 / fp16 supported License

This model is released under a custom license based on the Llama 3.1 Community License.

Users must comply with applicable terms when deploying or redistributing the model.

Downloads last month: 256

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for deepconradlabs/conrad-nit-5.1-8B

Base model

meta-llama/Llama-3.1-8B

Finetuned

(1435)

this model

deepconradlabs
/

conrad-nit-5.1-8B

You need to agree to share your contact information to access this model

Model tree for deepconradlabs/conrad-nit-5.1-8B

Space using deepconradlabs/conrad-nit-5.1-8B 1