Instructions to use sathiiiii/polyalign-gemma2-2b-en-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sathiiiii/polyalign-gemma2-2b-en-sft with Transformers:

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

pipe = pipeline("text-generation", model="sathiiiii/polyalign-gemma2-2b-en-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sathiiiii/polyalign-gemma2-2b-en-sft")
model = AutoModelForCausalLM.from_pretrained("sathiiiii/polyalign-gemma2-2b-en-sft", 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 sathiiiii/polyalign-gemma2-2b-en-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sathiiiii/polyalign-gemma2-2b-en-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sathiiiii/polyalign-gemma2-2b-en-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sathiiiii/polyalign-gemma2-2b-en-sft

SGLang

How to use sathiiiii/polyalign-gemma2-2b-en-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 "sathiiiii/polyalign-gemma2-2b-en-sft" \
    --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": "sathiiiii/polyalign-gemma2-2b-en-sft",
		"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 "sathiiiii/polyalign-gemma2-2b-en-sft" \
        --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": "sathiiiii/polyalign-gemma2-2b-en-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sathiiiii/polyalign-gemma2-2b-en-sft with Docker Model Runner:
```
docker model run hf.co/sathiiiii/polyalign-gemma2-2b-en-sft
```

polyalign-gemma2-2b-en-sft / README.md

sathiiiii

Add files using upload-large-folder tool

e998a6a verified 4 months ago

preview code

Raw

History Blame Contribute Delete

2.04 kB

	---
	library_name: transformers
	license: other
	base_model: google/gemma-2-2b
	tags:
	- llama-factory
	- full
	- generated_from_trainer
	model-index:
	- name: polyalign
	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. -->

	# polyalign

	This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on the polyalign_train dataset.
	It achieves the following results on the evaluation set:
	- Loss: 1.3660

	## 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: 1e-05
	- train_batch_size: 2
	- eval_batch_size: 2
	- seed: 42
	- distributed_type: multi-GPU
	- num_devices: 8
	- gradient_accumulation_steps: 4
	- total_train_batch_size: 64
	- total_eval_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: cosine
	- lr_scheduler_warmup_ratio: 0.1
	- num_epochs: 1.0
	- mixed_precision_training: Native AMP

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|
	\| 1.7654 \| 0.1095 \| 1000 \| 1.2028 \|
	\| 1.6802 \| 0.2190 \| 2000 \| 1.2025 \|
	\| 1.5967 \| 0.3285 \| 3000 \| 1.2402 \|
	\| 1.5228 \| 0.4380 \| 4000 \| 1.2522 \|
	\| 1.4704 \| 0.5475 \| 5000 \| 1.2775 \|
	\| 1.3997 \| 0.6570 \| 6000 \| 1.2849 \|
	\| 1.3373 \| 0.7666 \| 7000 \| 1.3272 \|
	\| 1.3105 \| 0.8761 \| 8000 \| 1.3563 \|
	\| 1.2906 \| 0.9856 \| 9000 \| 1.3660 \|


	### Framework versions

	- Transformers 4.56.2
	- Pytorch 2.9.1+rocm6.3
	- Datasets 4.0.0
	- Tokenizers 0.22.2