Instructions to use thedeba/gemma_bn_instruct_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thedeba/gemma_bn_instruct_v2 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("INSAIT-Institute/BgGPT-Gemma-2-2.6B-IT-v1.0")
model = PeftModel.from_pretrained(base_model, "thedeba/gemma_bn_instruct_v2")

Transformers

How to use thedeba/gemma_bn_instruct_v2 with Transformers:

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

pipe = pipeline("text-generation", model="thedeba/gemma_bn_instruct_v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("thedeba/gemma_bn_instruct_v2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use thedeba/gemma_bn_instruct_v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thedeba/gemma_bn_instruct_v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thedeba/gemma_bn_instruct_v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thedeba/gemma_bn_instruct_v2

SGLang

How to use thedeba/gemma_bn_instruct_v2 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 "thedeba/gemma_bn_instruct_v2" \
    --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": "thedeba/gemma_bn_instruct_v2",
		"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 "thedeba/gemma_bn_instruct_v2" \
        --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": "thedeba/gemma_bn_instruct_v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thedeba/gemma_bn_instruct_v2 with Docker Model Runner:
```
docker model run hf.co/thedeba/gemma_bn_instruct_v2
```

gemma_bn_instruct_v2 / README.md

thedeba

End of training

5908fe6 verified 9 months ago

preview code

raw

history blame contribute delete

2.12 kB

metadata

library_name: peft
license: gemma
base_model: INSAIT-Institute/BgGPT-Gemma-2-2.6B-IT-v1.0
tags:
  - base_model:adapter:INSAIT-Institute/BgGPT-Gemma-2-2.6B-IT-v1.0
  - lora
  - transformers
pipeline_tag: text-generation
model-index:
  - name: gemma_bn_instruct_v2
    results: []

gemma_bn_instruct_v2

This model is a fine-tuned version of INSAIT-Institute/BgGPT-Gemma-2-2.6B-IT-v1.0 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.5895

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: 1
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.8384	0.2768	200	1.8630
1.8637	0.5535	400	1.7923
1.7568	0.8303	600	1.6993
1.4292	1.1066	800	1.6683
1.5239	1.3833	1000	1.6333
1.585	1.6601	1200	1.5996
1.3414	1.9369	1400	1.5713
1.1018	2.2131	1600	1.6156
1.1496	2.4899	1800	1.5968
1.106	2.7666	2000	1.5895

Framework versions

PEFT 0.17.0
Transformers 4.51.3
Pytorch 2.7.0+cu126
Datasets 4.0.0
Tokenizers 0.21.1