Instructions to use misukisu/whatsapp-twin-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use misukisu/whatsapp-twin-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="misukisu/whatsapp-twin-bf16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("misukisu/whatsapp-twin-bf16")
model = AutoModelForCausalLM.from_pretrained("misukisu/whatsapp-twin-bf16", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use misukisu/whatsapp-twin-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "misukisu/whatsapp-twin-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "misukisu/whatsapp-twin-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/misukisu/whatsapp-twin-bf16

SGLang

How to use misukisu/whatsapp-twin-bf16 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 "misukisu/whatsapp-twin-bf16" \
    --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": "misukisu/whatsapp-twin-bf16",
		"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 "misukisu/whatsapp-twin-bf16" \
        --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": "misukisu/whatsapp-twin-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use misukisu/whatsapp-twin-bf16 with Docker Model Runner:
```
docker model run hf.co/misukisu/whatsapp-twin-bf16
```

whatsapp-twin-bf16

Standalone bf16 model: Qwen3-4B-Instruct-2507 with a LoRA adapter fused in. Fine-tuned to reply in the owner's voice in a WhatsApp chat (~1k context→reply examples, mask_prompt training, iter-600 checkpoint selected by validation loss).

This is the GPU/server-friendly copy — standard HF safetensors, loads in plain transformers. For Apple Silicon, prefer the 8-bit MLX version: misukisu/whatsapp-twin-8bit. The MLX LoRA adapter is at misukisu/whatsapp-twin-lora.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("misukisu/whatsapp-twin-bf16")
model = AutoModelForCausalLM.from_pretrained(
    "misukisu/whatsapp-twin-bf16", dtype=torch.bfloat16, device_map="cuda"
)

msgs = [
    {"role": "system", "content": "You are Miska replying in a WhatsApp chat. Given the recent transcript, write Miska's next message in their exact voice — same casing, punctuation, emoji habits and length. Output only the message text, nothing else."},
    {"role": "user", "content": "Aatu: moi pelataaks tänää"},
]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True,
                              return_tensors="pt", return_dict=True).to(model.device)
out = model.generate(**ids, max_new_tokens=80, do_sample=True,
                     temperature=0.75, top_p=0.9,
                     pad_token_id=tok.eos_token_id)
print(tok.decode(out[0][ids["input_ids"].shape[-1]:], skip_special_tokens=True))

Privacy

Weights are derived from private chat data. The model was published at the owner's request; no chat transcripts are included in this repo. The model can be prompted to generate text in the owner's conversational style.

Downloads last month: 219

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for misukisu/whatsapp-twin-bf16

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5890)

this model