Instructions to use kitsunea/modelSmolLM2-improvd-assignment2-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kitsunea/modelSmolLM2-improvd-assignment2-2 with Transformers:

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

pipe = pipeline("text-generation", model="kitsunea/modelSmolLM2-improvd-assignment2-2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kitsunea/modelSmolLM2-improvd-assignment2-2")
model = AutoModelForCausalLM.from_pretrained("kitsunea/modelSmolLM2-improvd-assignment2-2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kitsunea/modelSmolLM2-improvd-assignment2-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kitsunea/modelSmolLM2-improvd-assignment2-2"
# 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-assignment2-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kitsunea/modelSmolLM2-improvd-assignment2-2

SGLang

How to use kitsunea/modelSmolLM2-improvd-assignment2-2 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-assignment2-2" \
    --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-assignment2-2",
		"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-assignment2-2" \
        --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-assignment2-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kitsunea/modelSmolLM2-improvd-assignment2-2 with Docker Model Runner:
```
docker model run hf.co/kitsunea/modelSmolLM2-improvd-assignment2-2
```

modelSmolLM2-improvd-assignment2-2 / README.md

kitsunea

End of training

ba7366d verified 11 months ago

preview code

Raw

History Blame Contribute Delete

2.35 kB

metadata

library_name: transformers
license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-135M
tags:
  - generated_from_trainer
model-index:
  - name: modelSmolLM2-improvd-assignment2-2
    results: []

modelSmolLM2-improvd-assignment2-2

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.2993

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: 0.0003
train_batch_size: 16
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
2.9887	0.1067	200	2.9221
2.7337	0.2133	400	2.7976
2.6423	0.32	600	2.7118
2.534	0.4267	800	2.6432
2.4911	0.5333	1000	2.5883
2.4906	0.64	1200	2.5351
2.4029	0.7467	1400	2.4751
2.3421	0.8533	1600	2.4331
2.3091	0.96	1800	2.3934
1.9326	1.0667	2000	2.4085
1.7083	1.1733	2200	2.3911
1.6905	1.28	2400	2.3594
1.6651	1.3867	2600	2.3497
1.647	1.4933	2800	2.3315
1.6486	1.6	3000	2.3155
1.6093	1.7067	3200	2.3068
1.6538	1.8133	3400	2.3016
1.6138	1.92	3600	2.2993

Framework versions

Transformers 4.56.1
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.0