Instructions to use Ailonordsletta/Nanbeige4.1-3B-microthink with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ailonordsletta/Nanbeige4.1-3B-microthink with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Nanbeige/Nanbeige4.1-3B")
model = PeftModel.from_pretrained(base_model, "Ailonordsletta/Nanbeige4.1-3B-microthink")

Transformers

How to use Ailonordsletta/Nanbeige4.1-3B-microthink with Transformers:

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

pipe = pipeline("text-generation", model="Ailonordsletta/Nanbeige4.1-3B-microthink")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ailonordsletta/Nanbeige4.1-3B-microthink")
model = AutoModelForCausalLM.from_pretrained("Ailonordsletta/Nanbeige4.1-3B-microthink", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ailonordsletta/Nanbeige4.1-3B-microthink with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ailonordsletta/Nanbeige4.1-3B-microthink"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ailonordsletta/Nanbeige4.1-3B-microthink",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ailonordsletta/Nanbeige4.1-3B-microthink

SGLang

How to use Ailonordsletta/Nanbeige4.1-3B-microthink 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 "Ailonordsletta/Nanbeige4.1-3B-microthink" \
    --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": "Ailonordsletta/Nanbeige4.1-3B-microthink",
		"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 "Ailonordsletta/Nanbeige4.1-3B-microthink" \
        --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": "Ailonordsletta/Nanbeige4.1-3B-microthink",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ailonordsletta/Nanbeige4.1-3B-microthink with Docker Model Runner:
```
docker model run hf.co/Ailonordsletta/Nanbeige4.1-3B-microthink
```

See axolotl config

axolotl version: 0.13.0.dev0

base_model: Nanbeige/Nanbeige4.1-3B
trust_remote_code: true

# Dataset
datasets:
  - path: Ailonordsletta/med-dict
    type: chat_template
chat_template: tokenizer_default

# LoRA
adapter: lora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
  - gate_proj
  - down_proj
  - up_proj
load_in_8bit: true

# Training
num_epochs: 3
micro_batch_size: 4
gradient_accumulation_steps: 4
learning_rate: 2e-4
lr_scheduler: cosine
warmup_ratio: 0.05
optimizer: adamw_bnb_8bit
sequence_len: 4096
train_on_inputs: false

# Precision
bf16: auto

# Saving
output_dir: ./outputs/nanbeige-microthink
save_strategy: steps
save_steps: 200
save_total_limit: 3
logging_steps: 10
gradient_checkpointing: true

seed: 42

outputs/nanbeige-microthink

This model is a fine-tuned version of Nanbeige/Nanbeige4.1-3B on the Ailonordsletta/med-dict dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 46
training_steps: 929

Training results

Framework versions

PEFT 0.17.1
Transformers 4.57.0
Pytorch 2.7.1+cu126
Datasets 4.0.0
Tokenizers 0.22.1

Downloads last month: 3

Model tree for Ailonordsletta/Nanbeige4.1-3B-microthink

Base model

Nanbeige/Nanbeige4-3B-Base

Finetuned

Nanbeige/Nanbeige4.1-3B

Adapter

(7)

this model