Instructions to use VikrantRamesh/Llama-2-CN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VikrantRamesh/Llama-2-CN with Transformers:

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

pipe = pipeline("text-generation", model="VikrantRamesh/Llama-2-CN")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("VikrantRamesh/Llama-2-CN")
model = AutoModelForMultimodalLM.from_pretrained("VikrantRamesh/Llama-2-CN")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use VikrantRamesh/Llama-2-CN with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VikrantRamesh/Llama-2-CN"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VikrantRamesh/Llama-2-CN",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/VikrantRamesh/Llama-2-CN

SGLang

How to use VikrantRamesh/Llama-2-CN 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 "VikrantRamesh/Llama-2-CN" \
    --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": "VikrantRamesh/Llama-2-CN",
		"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 "VikrantRamesh/Llama-2-CN" \
        --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": "VikrantRamesh/Llama-2-CN",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use VikrantRamesh/Llama-2-CN with Docker Model Runner:
```
docker model run hf.co/VikrantRamesh/Llama-2-CN
```

Llama-2-CN

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

Loss: 2.4423

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
3.3431	0.03	10	3.1212
2.8976	0.05	20	2.7770
2.6878	0.08	30	2.6526
2.6344	0.1	40	2.5690
2.5165	0.13	50	2.5212
2.5377	0.15	60	2.4917
2.4577	0.18	70	2.4712
2.4309	0.21	80	2.4562
2.3986	0.23	90	2.4465
2.4445	0.26	100	2.4423

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2

Downloads last month: 3

Model tree for VikrantRamesh/Llama-2-CN

Base model

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

Quantized

(101)

this model

VikrantRamesh
/

Llama-2-CN

Llama-2-CN

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for VikrantRamesh/Llama-2-CN

Space using VikrantRamesh/Llama-2-CN 1