Instructions to use Nikolester0/Gyaanchand-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nikolester0/Gyaanchand-3B with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "Nikolester0/Gyaanchand-3B")

Transformers

How to use Nikolester0/Gyaanchand-3B with Transformers:

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

pipe = pipeline("text-generation", model="Nikolester0/Gyaanchand-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Nikolester0/Gyaanchand-3B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Nikolester0/Gyaanchand-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nikolester0/Gyaanchand-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nikolester0/Gyaanchand-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nikolester0/Gyaanchand-3B

SGLang

How to use Nikolester0/Gyaanchand-3B 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 "Nikolester0/Gyaanchand-3B" \
    --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": "Nikolester0/Gyaanchand-3B",
		"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 "Nikolester0/Gyaanchand-3B" \
        --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": "Nikolester0/Gyaanchand-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Nikolester0/Gyaanchand-3B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Nikolester0/Gyaanchand-3B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Nikolester0/Gyaanchand-3B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Nikolester0/Gyaanchand-3B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Nikolester0/Gyaanchand-3B",
    max_seq_length=2048,
)

Docker Model Runner
How to use Nikolester0/Gyaanchand-3B with Docker Model Runner:
```
docker model run hf.co/Nikolester0/Gyaanchand-3B
```

Model Card for Model ID

Gyaanchand-3B — instruction-tuned conversational model fine-tuned with LoRA/PEFT on top of an Unsloth LLaMA-3.2-3B base. This model is optimized for instruction-following, conversational QA and assistant-style outputs.

Model Details

Model Description

Gyaanchand-3B is a LoRA / PEFT fine-tuned variant of unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit. It was fine-tuned using Unsloth/Transformers/TRL tooling with safetensors-format adapters and is intended for general-purpose conversational and instruction-following tasks in English.

Developed by: Nikolester0
Funded by [optional]: Not disclosed
Shared by [optional]: Nikolester0
Model type: Instruction-tuned causal language model (LLaMA family, 3B) with PEFT/LoRA adapters
Language(s) (NLP): English (primary)
License: Apache-2.0 (see base model license)
Finetuned from model [optional]: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit (adapter / LoRA checkpoint uploaded to this repo)

Model Sources [optional]

Repository: https://huggingface.co/Nikolester0/Gyaanchand-3B
Paper [optional]: Base model papers as applicable to LLaMA/Unsloth (see base model page)
Demo [optional]: None hosted

Uses

Direct Use

This model is intended for:

Conversational AI / chat assistants
Instruction following (SFT-style prompts)
Educational Q&A and explanation generation
Research and experimentation with PEFT adapters

Downstream Use [optional]

Further fine-tuning for domain-specific chatbots
Integration into chat UI frontends or research pipelines
Use as a base for controlled generation via prompts and RLHF-style wrappers

Out-of-Scope Use

High-stakes professional advice (medical, legal, financial) without human oversight
Generation of illegal, violent, or hateful content

Bias, Risks, and Limitations

This model inherits general LLaMA-style limitations and possible dataset biases. It may:

Produce incorrect or hallucinated facts
Reflect undesirable biases present in training data
Fail on specialized domain reasoning or up-to-date factual queries

Recommendations

Use a human-in-the-loop for high-stakes outputs.
Add prompt-based guardrails and filtering for unsafe content.
Test on your target inputs before production deployment.

How to Get Started with the Model

Example (Python Transformers):

from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig

model_id = "Nikolester0/Gyaanchand-3B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)  # if required by base model

prompt = "Explain how neural networks learn, step by step."
inputs = tokenizer(prompt, return_tensors="pt")
generate_kwargs = {"max_new_tokens": 200, "temperature": 0.7}
outputs = model.generate(**inputs, **generate_kwargs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 1