Instructions to use ueihieu/llama2-7b-lora-rebel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ueihieu/llama2-7b-lora-rebel with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-7b-hf")
model = PeftModel.from_pretrained(base_model, "ueihieu/llama2-7b-lora-rebel")

Transformers

How to use ueihieu/llama2-7b-lora-rebel with Transformers:

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

pipe = pipeline("text-generation", model="ueihieu/llama2-7b-lora-rebel")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ueihieu/llama2-7b-lora-rebel", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ueihieu/llama2-7b-lora-rebel with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ueihieu/llama2-7b-lora-rebel"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ueihieu/llama2-7b-lora-rebel",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ueihieu/llama2-7b-lora-rebel

SGLang

How to use ueihieu/llama2-7b-lora-rebel 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 "ueihieu/llama2-7b-lora-rebel" \
    --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": "ueihieu/llama2-7b-lora-rebel",
		"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 "ueihieu/llama2-7b-lora-rebel" \
        --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": "ueihieu/llama2-7b-lora-rebel",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ueihieu/llama2-7b-lora-rebel with Docker Model Runner:
```
docker model run hf.co/ueihieu/llama2-7b-lora-rebel
```

llama2-7b-lora-rebel

This model is a fine-tuned version of NousResearch/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.8091

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: 0.0003
train_batch_size: 8
eval_batch_size: 8
seed: 42
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: 100
training_steps: 500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
9.5316	0.0006	20	9.1564
5.5820	0.0012	40	5.0022
3.1964	0.0018	60	3.2908
3.0524	0.0024	80	2.9273
2.9086	0.0030	100	2.8656
2.9885	0.0036	120	2.8475
3.0935	0.0042	140	2.8373
2.9271	0.0048	160	2.8356
2.8657	0.0054	180	2.8280
2.7070	0.0060	200	2.8244
2.9717	0.0066	220	2.8218
2.8754	0.0072	240	2.8200
2.8520	0.0078	260	2.8178
2.4384	0.0084	280	2.8158
2.9701	0.0090	300	2.8149
2.8678	0.0096	320	2.8139
2.7211	0.0102	340	2.8127
2.7630	0.0108	360	2.8123
2.8834	0.0114	380	2.8115
2.8540	0.0120	400	2.8110
2.9288	0.0126	420	2.8114
2.7809	0.0132	440	2.8099
2.8883	0.0138	460	2.8094
2.7767	0.0144	480	2.8092
2.6354	0.0150	500	2.8091

Framework versions

PEFT 0.18.1
Transformers 5.2.0
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.2

Downloads last month: 2

Model tree for ueihieu/llama2-7b-lora-rebel

Base model

NousResearch/Llama-2-7b-hf

Adapter

(139)

this model