Instructions to use imonetizeitbd/affiliate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use imonetizeitbd/affiliate with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-3-4b-it-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "imonetizeitbd/affiliate")

Transformers

How to use imonetizeitbd/affiliate with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("imonetizeitbd/affiliate", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use imonetizeitbd/affiliate with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/imonetizeitbd/affiliate

SGLang

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

Unsloth Desktop
Docker Model Runner
How to use imonetizeitbd/affiliate with Docker Model Runner:
```
docker model run hf.co/imonetizeitbd/affiliate
```

Affiliate Screening LLM

This is a LoRA adapter fine-tuned on unsloth/gemma-3-4b-it for affiliate screening tasks. It acts as an AI Manager that screens affiliate applications, verifies answers, and enforces network policies.

🚀 Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

# বেস মডেল লোড করুন
base_model = AutoModelForCausalLM.from_pretrained(
    "unsloth/gemma-3-4b-it",
    torch_dtype=torch.float16,
    device_map="auto"
)

# LoRA অ্যাডাপ্টার লোড করুন
model = PeftModel.from_pretrained(
    base_model,
    "imonetizeitbd/affiliate"
)

tokenizer = AutoTokenizer.from_pretrained("unsloth/gemma-3-4b-it")

# টেস্ট
prompt = "You are AI Manager, the affiliate screening assistant. What is your name?"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 17

Model tree for imonetizeitbd/affiliate

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

unsloth/gemma-3-4b-it-unsloth-bnb-4bit

Adapter

(128)

this model