Instructions to use kitsunea/modelSmolLM2-improvd-assignment2-exercise with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kitsunea/modelSmolLM2-improvd-assignment2-exercise with Transformers:

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

pipe = pipeline("text-generation", model="kitsunea/modelSmolLM2-improvd-assignment2-exercise")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kitsunea/modelSmolLM2-improvd-assignment2-exercise")
model = AutoModelForCausalLM.from_pretrained("kitsunea/modelSmolLM2-improvd-assignment2-exercise", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kitsunea/modelSmolLM2-improvd-assignment2-exercise with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kitsunea/modelSmolLM2-improvd-assignment2-exercise"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kitsunea/modelSmolLM2-improvd-assignment2-exercise",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kitsunea/modelSmolLM2-improvd-assignment2-exercise

SGLang

How to use kitsunea/modelSmolLM2-improvd-assignment2-exercise 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 "kitsunea/modelSmolLM2-improvd-assignment2-exercise" \
    --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": "kitsunea/modelSmolLM2-improvd-assignment2-exercise",
		"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 "kitsunea/modelSmolLM2-improvd-assignment2-exercise" \
        --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": "kitsunea/modelSmolLM2-improvd-assignment2-exercise",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kitsunea/modelSmolLM2-improvd-assignment2-exercise with Docker Model Runner:
```
docker model run hf.co/kitsunea/modelSmolLM2-improvd-assignment2-exercise
```

modelSmolLM2-improvd-assignment2-exercise / README.md

kitsunea

End of training

af81b7e verified 10 months ago

preview code

Raw

History Blame Contribute Delete

2.36 kB

	---
	library_name: transformers
	license: apache-2.0
	base_model: HuggingFaceTB/SmolLM2-135M
	tags:
	- generated_from_trainer
	model-index:
	- name: modelSmolLM2-improvd-assignment2-exercise
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# modelSmolLM2-improvd-assignment2-exercise

	This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Loss: 2.2899

	## 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: 0.0001
	- train_batch_size: 8
	- eval_batch_size: 8
	- seed: 42
	- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: cosine
	- num_epochs: 2

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|
	\| 2.9359 \| 0.1067 \| 400 \| 2.7948 \|
	\| 2.6792 \| 0.2133 \| 800 \| 2.6778 \|
	\| 2.5989 \| 0.32 \| 1200 \| 2.6008 \|
	\| 2.5019 \| 0.4267 \| 1600 \| 2.5441 \|
	\| 2.4683 \| 0.5333 \| 2000 \| 2.4983 \|
	\| 2.4736 \| 0.64 \| 2400 \| 2.4578 \|
	\| 2.3997 \| 0.7467 \| 2800 \| 2.4135 \|
	\| 2.3478 \| 0.8533 \| 3200 \| 2.3831 \|
	\| 2.3269 \| 0.96 \| 3600 \| 2.3529 \|
	\| 2.0474 \| 1.0667 \| 4000 \| 2.3547 \|
	\| 1.8848 \| 1.1733 \| 4400 \| 2.3444 \|
	\| 1.87 \| 1.28 \| 4800 \| 2.3280 \|
	\| 1.8541 \| 1.3867 \| 5200 \| 2.3183 \|
	\| 1.8413 \| 1.4933 \| 5600 \| 2.3095 \|
	\| 1.8518 \| 1.6 \| 6000 \| 2.2993 \|
	\| 1.8189 \| 1.7067 \| 6400 \| 2.2945 \|
	\| 1.8615 \| 1.8133 \| 6800 \| 2.2911 \|
	\| 1.82 \| 1.92 \| 7200 \| 2.2899 \|


	### Framework versions

	- Transformers 4.57.1
	- Pytorch 2.8.0+cu126
	- Datasets 4.0.0
	- Tokenizers 0.22.1