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

Libraries

How to use ueihieu/llama2-7b-lora-scierc 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-scierc")

Transformers

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

llama2-7b-lora-scierc

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: 1.6978

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
5.6120	0.0361	20	5.1342
2.9998	0.0722	40	3.1167
2.7886	0.1083	60	2.6022
2.3549	0.1444	80	2.3743
2.0507	0.1805	100	2.3204
2.2334	0.2166	120	2.2844
2.0928	0.2527	140	2.2521
2.3828	0.2888	160	2.2191
2.2091	0.3249	180	2.1864
2.1972	0.3610	200	2.1520
2.0895	0.3971	220	2.1100
2.2188	0.4332	240	2.0672
2.0837	0.4693	260	2.0319
2.0093	0.5054	280	1.9877
1.9424	0.5415	300	1.9441
2.0697	0.5776	320	1.9027
1.9542	0.6137	340	1.8772
1.6690	0.6498	360	1.8424
1.8379	0.6859	380	1.8040
1.9799	0.7220	400	1.7791
1.8926	0.7581	420	1.7500
1.7145	0.7942	440	1.7267
1.8679	0.8303	460	1.7114
1.9494	0.8664	480	1.7028
1.7245	0.9025	500	1.6978

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: 1

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

Base model

NousResearch/Llama-2-7b-hf

Adapter

(139)

this model