Instructions to use timdef/smollm3-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use timdef/smollm3-sft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="timdef/smollm3-sft")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("timdef/smollm3-sft") model = AutoModelForCausalLM.from_pretrained("timdef/smollm3-sft") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use timdef/smollm3-sft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "timdef/smollm3-sft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "timdef/smollm3-sft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/timdef/smollm3-sft
- SGLang
How to use timdef/smollm3-sft 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 "timdef/smollm3-sft" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "timdef/smollm3-sft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "timdef/smollm3-sft" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "timdef/smollm3-sft", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use timdef/smollm3-sft with Docker Model Runner:
docker model run hf.co/timdef/smollm3-sft
End of training
Browse files
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
base_model: HuggingFaceTB/SmolLM3-3B-Base
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
model_name: smollm3-sft
|
| 5 |
tags:
|
|
@@ -14,7 +15,7 @@ licence: license
|
|
| 14 |
|
| 15 |
# Model Card for smollm3-sft
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [HuggingFaceTB/SmolLM3-3B-Base](https://huggingface.co/HuggingFaceTB/SmolLM3-3B-Base).
|
| 18 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 19 |
|
| 20 |
## Quick start
|
|
|
|
| 1 |
---
|
| 2 |
base_model: HuggingFaceTB/SmolLM3-3B-Base
|
| 3 |
+
datasets: HuggingFaceTB/smoltalk2_everyday_convs_think
|
| 4 |
library_name: transformers
|
| 5 |
model_name: smollm3-sft
|
| 6 |
tags:
|
|
|
|
| 15 |
|
| 16 |
# Model Card for smollm3-sft
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [HuggingFaceTB/SmolLM3-3B-Base](https://huggingface.co/HuggingFaceTB/SmolLM3-3B-Base) on the [HuggingFaceTB/smoltalk2_everyday_convs_think](https://huggingface.co/datasets/HuggingFaceTB/smoltalk2_everyday_convs_think) dataset.
|
| 19 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 20 |
|
| 21 |
## Quick start
|