Instructions to use trikohung/blockchain-qlora-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trikohung/blockchain-qlora-model with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-1b-it")
model = PeftModel.from_pretrained(base_model, "trikohung/blockchain-qlora-model")

Transformers

How to use trikohung/blockchain-qlora-model with Transformers:

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

pipe = pipeline("text-generation", model="trikohung/blockchain-qlora-model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("trikohung/blockchain-qlora-model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trikohung/blockchain-qlora-model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/trikohung/blockchain-qlora-model

SGLang

How to use trikohung/blockchain-qlora-model 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 "trikohung/blockchain-qlora-model" \
    --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": "trikohung/blockchain-qlora-model",
		"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 "trikohung/blockchain-qlora-model" \
        --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": "trikohung/blockchain-qlora-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trikohung/blockchain-qlora-model with Docker Model Runner:
```
docker model run hf.co/trikohung/blockchain-qlora-model
```

blockchain-qlora-model

This model is a fine-tuned version of google/gemma-3-1b-it on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.9171

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: 0.0002
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 2
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.5328	1.0	1	3.4875
3.5328	2.0	2	3.4309
3.4749	3.0	3	3.3168
3.3569	4.0	4	3.2170
3.2524	5.0	5	3.1308
3.1635	6.0	6	3.0589
3.0883	7.0	7	3.0017
3.0338	8.0	8	2.9593
2.9889	9.0	9	2.9312
2.9613	10.0	10	2.9171

Framework versions

PEFT 0.17.1
Transformers 4.56.2
Pytorch 2.8.0+cpu
Datasets 4.1.1
Tokenizers 0.22.1

Downloads last month: 13

Model tree for trikohung/blockchain-qlora-model

Base model

google/gemma-3-1b-pt

Finetuned

google/gemma-3-1b-it

Adapter

(219)

this model