Instructions to use xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-2-9b-it")
model = PeftModel.from_pretrained(base_model, "xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all")

Transformers

How to use xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all with Transformers:

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

pipe = pipeline("text-generation", model="xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all")
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("xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all

SGLang

How to use xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all 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 "xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all" \
    --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": "xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all",
		"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 "xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all" \
        --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": "xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all with Docker Model Runner:
```
docker model run hf.co/xummer/gemma2-9b-nli-P2-multi-n500-seed42-lora-all
```

gemma2-9b-nli-P2-multi-n500-seed42-lora-all / README.md

xummer

Upload folder using huggingface_hub

04824d7 verified 5 months ago

preview code

Raw History Blame Contribute Delete

1.76 kB

metadata

library_name: peft
license: other
base_model: google/gemma-2-9b-it
tags:
  - base_model:adapter:google/gemma-2-9b-it
  - llama-factory
  - lora
  - transformers
metrics:
  - accuracy
pipeline_tag: text-generation
model-index:
  - name: nli_P2_multi_n500_seed42
    results: []

nli_P2_multi_n500_seed42

This model is a fine-tuned version of google/gemma-2-9b-it on the nli_multi_n500_train dataset. It achieves the following results on the evaluation set:

Loss: 0.2139
Accuracy: 0.9458
Mcq Accuracy: 0.7311

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_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_steps: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Mcq Accuracy
0.0458	1.7751	500	0.1556	0.9427	0.7222

Framework versions

PEFT 0.18.1
Transformers 5.2.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2