Instructions to use adityashukzy/full_finetuning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adityashukzy/full_finetuning with Transformers:

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

pipe = pipeline("text-generation", model="adityashukzy/full_finetuning")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adityashukzy/full_finetuning")
model = AutoModelForCausalLM.from_pretrained("adityashukzy/full_finetuning", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use adityashukzy/full_finetuning with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/adityashukzy/full_finetuning

SGLang

How to use adityashukzy/full_finetuning 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 "adityashukzy/full_finetuning" \
    --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": "adityashukzy/full_finetuning",
		"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 "adityashukzy/full_finetuning" \
        --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": "adityashukzy/full_finetuning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use adityashukzy/full_finetuning with Docker Model Runner:
```
docker model run hf.co/adityashukzy/full_finetuning
```

full_finetuning / README.md

adityashukzy

Adi's training complete!

6750bcd verified 9 months ago

preview code

Raw

History Blame Contribute Delete

2.04 kB

	---
	library_name: transformers
	license: apache-2.0
	base_model: HuggingFaceTB/SmolLM2-135M
	tags:
	- causal-language-model
	- generated_from_trainer
	model-index:
	- name: full_finetuning
	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. -->

	# full_finetuning

	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: 0.9702

	## 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: 2e-05
	- train_batch_size: 2
	- eval_batch_size: 2
	- seed: 42
	- gradient_accumulation_steps: 8
	- total_train_batch_size: 16
	- 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: linear
	- lr_scheduler_warmup_ratio: 0.1
	- num_epochs: 10
	- mixed_precision_training: Native AMP

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:-----:\|:----:\|:---------------:\|
	\| 1.0076 \| 1.0 \| 142 \| 1.0190 \|
	\| 0.9486 \| 2.0 \| 284 \| 0.9752 \|
	\| 0.8546 \| 3.0 \| 426 \| 0.9600 \|
	\| 0.808 \| 4.0 \| 568 \| 0.9541 \|
	\| 0.7807 \| 5.0 \| 710 \| 0.9538 \|
	\| 0.7284 \| 6.0 \| 852 \| 0.9560 \|
	\| 0.7251 \| 7.0 \| 994 \| 0.9609 \|
	\| 0.6856 \| 8.0 \| 1136 \| 0.9648 \|
	\| 0.6421 \| 9.0 \| 1278 \| 0.9684 \|
	\| 0.6344 \| 10.0 \| 1420 \| 0.9702 \|


	### Framework versions

	- Transformers 4.57.2
	- Pytorch 2.9.0+cu126
	- Datasets 4.0.0
	- Tokenizers 0.22.1