Instructions to use prithivMLmods/Primal-Mini-3B-Exp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Primal-Mini-3B-Exp with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Primal-Mini-3B-Exp")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Primal-Mini-3B-Exp")
model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Primal-Mini-3B-Exp")
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

vLLM

How to use prithivMLmods/Primal-Mini-3B-Exp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Primal-Mini-3B-Exp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Primal-Mini-3B-Exp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Primal-Mini-3B-Exp

SGLang

How to use prithivMLmods/Primal-Mini-3B-Exp 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 "prithivMLmods/Primal-Mini-3B-Exp" \
    --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": "prithivMLmods/Primal-Mini-3B-Exp",
		"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 "prithivMLmods/Primal-Mini-3B-Exp" \
        --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": "prithivMLmods/Primal-Mini-3B-Exp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prithivMLmods/Primal-Mini-3B-Exp with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Primal-Mini-3B-Exp
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Primal-Mini-3B-Exp

Primal-Mini-3B-Exp is based on the Qwen 3B modality architecture, designed to enhance the reasoning capabilities of 3B-parameter models. It has been fine-tuned on a synthetic dataset derived from a subset of Qwen’s QWQ and DeepSeek R1, further optimizing its chain-of-thought (CoT) reasoning and logical problem-solving abilities. The model demonstrates significant improvements in context understanding, structured data processing, and long-context comprehension, making it ideal for complex reasoning tasks, instruction-following, and text generation.

Key Improvements

Advanced Reasoning & Logic: Optimized for multi-step problem-solving, logical deduction, and contextual analysis.
Fine-Tuned Instruction Following: Generates precise responses, structured outputs (e.g., JSON), and extended long-form text (4K+ tokens).
Greater Adaptability: Excels in role-playing, multi-turn dialogues, and diverse system prompts.
Long-Context Support: Handles up to 64K tokens and generates up to 4K tokens per output.
Multilingual Proficiency: Supports over 20 languages, including Chinese, English, French, Spanish, Portuguese, German, and more.

Quickstart with Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "prithivMLmods/Primal-Mini-3B-Exp"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Explain the concept of logical reasoning in AI."
messages = [
    {"role": "system", "content": "You are an expert AI assistant specialized in reasoning and logic."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=256
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Intended Use

Advanced Logical & Analytical Reasoning: Designed for problem-solving, multi-step deductions, and cognitive reasoning tasks.
Mathematical & Scientific Computation: Supports theorem proving, complex calculations, and scientific knowledge retrieval.
Code Generation & Debugging: Generates optimized code, detects errors, and improves programming workflows.
Structured Data Analysis: Processes tables, JSON, and structured formats for data-centric applications.
Multilingual Reasoning & Translation: High proficiency across 20+ languages for international applications.
Extended Text Generation: Capable of generating research papers, instructional guides, and in-depth reports.

Limitations

Moderate Computational Requirements: Requires mid-end consumer GPUs for optimal inference.
Language-Specific Variability: Performance may differ across supported languages, especially for low-resource languages.
Potential Error Accumulation: Long-form text generation can introduce inconsistencies over extended outputs.
Limited Real-World Awareness: Knowledge is restricted to training data and may not reflect recent world events.
Prompt Sensitivity: The quality of responses depends on the specificity and clarity of the input prompt.