Instructions to use sudipto-ducs/InLegalLLaMA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sudipto-ducs/InLegalLLaMA with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sudipto-ducs/InLegalLLaMA")
model = AutoModelForCausalLM.from_pretrained("sudipto-ducs/InLegalLLaMA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sudipto-ducs/InLegalLLaMA with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sudipto-ducs/InLegalLLaMA

SGLang

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

Docker Model Runner
How to use sudipto-ducs/InLegalLLaMA with Docker Model Runner:
```
docker model run hf.co/sudipto-ducs/InLegalLLaMA
```

InLegalLLaMA

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the inlegalllama-laws and the inlegalllama-sci datasets.

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: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 2000
num_epochs: 3.0
mixed_precision_training: Native AMP

Training results

Framework versions

PEFT 0.10.0
Transformers 4.39.0
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Downloads last month: 106

Safetensors

Model size

7B params

Tensor type

F16

Model tree for sudipto-ducs/InLegalLLaMA

Base model

meta-llama/Llama-2-7b-hf

Finetuned

(971)

this model

Finetunes

1 model

sudipto-ducs
/

InLegalLLaMA

InLegalLLaMA

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for sudipto-ducs/InLegalLLaMA

Dataset used to train sudipto-ducs/InLegalLLaMA