Instructions to use terrytaylorbonn/431_smollmv3_CPLT29 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use terrytaylorbonn/431_smollmv3_CPLT29 with Transformers:

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

pipe = pipeline("text-generation", model="terrytaylorbonn/431_smollmv3_CPLT29")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("terrytaylorbonn/431_smollmv3_CPLT29")
model = AutoModelForCausalLM.from_pretrained("terrytaylorbonn/431_smollmv3_CPLT29", 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 terrytaylorbonn/431_smollmv3_CPLT29 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "terrytaylorbonn/431_smollmv3_CPLT29"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "terrytaylorbonn/431_smollmv3_CPLT29",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/terrytaylorbonn/431_smollmv3_CPLT29

SGLang

How to use terrytaylorbonn/431_smollmv3_CPLT29 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 "terrytaylorbonn/431_smollmv3_CPLT29" \
    --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": "terrytaylorbonn/431_smollmv3_CPLT29",
		"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 "terrytaylorbonn/431_smollmv3_CPLT29" \
        --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": "terrytaylorbonn/431_smollmv3_CPLT29",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use terrytaylorbonn/431_smollmv3_CPLT29 with Docker Model Runner:
```
docker model run hf.co/terrytaylorbonn/431_smollmv3_CPLT29
```

Fine-tuned SmolLM Model

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-1.7B-Instruct.

Training Details

Base Model: HuggingFaceTB/SmolLM2-1.7B-Instruct
Fine-tuning Method: LoRA (Low-Rank Adaptation)
Hardware: NVIDIA RTX 3050 (4GB VRAM)
Framework: PyTorch + Transformers + PEFT

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

# Load model
tokenizer = AutoTokenizer.from_pretrained("terrytaylorbonn/431_smollmv3_CPLT29")
model = AutoModelForCausalLM.from_pretrained("terrytaylorbonn/431_smollmv3_CPLT29")

# Generate text
messages = [{"role": "user", "content": "Your prompt here"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=200)
response = tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True)
print(response)

Training Configuration

Batch Size: 1 (with gradient accumulation)
Learning Rate: 2e-4
LoRA Rank: 16
LoRA Alpha: 32
Training Steps: Variable based on dataset

Limitations

This model inherits the limitations of the base model and may have additional biases from the fine-tuning data.

Downloads last month: 9

Safetensors

Model size

2B params

Tensor type

F32

Model tree for terrytaylorbonn/431_smollmv3_CPLT29

Base model

HuggingFaceTB/SmolLM2-1.7B

Quantized

HuggingFaceTB/SmolLM2-1.7B-Instruct

Finetuned

(155)

this model