Instructions to use RedHatAI/Llama-2-7b-ultrachat200k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Llama-2-7b-ultrachat200k with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Llama-2-7b-ultrachat200k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Llama-2-7b-ultrachat200k")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/Llama-2-7b-ultrachat200k")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RedHatAI/Llama-2-7b-ultrachat200k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Llama-2-7b-ultrachat200k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Llama-2-7b-ultrachat200k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RedHatAI/Llama-2-7b-ultrachat200k

SGLang

How to use RedHatAI/Llama-2-7b-ultrachat200k 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 "RedHatAI/Llama-2-7b-ultrachat200k" \
    --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": "RedHatAI/Llama-2-7b-ultrachat200k",
		"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 "RedHatAI/Llama-2-7b-ultrachat200k" \
        --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": "RedHatAI/Llama-2-7b-ultrachat200k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RedHatAI/Llama-2-7b-ultrachat200k with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Llama-2-7b-ultrachat200k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-2-7b-ultrachat

This repo contains a Llama 2 7B finetuned for chat tasks using the UltraChat 200k dataset.

Official model weights from Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment.

Authors: Neural Magic, Cerebras

Usage

Below we share some code snippets on how to get quickly started with running the model.

Sparse Transfer

By leveraging a pre-sparsified model's structure, you can efficiently fine-tune on new data, leading to reduced hyperparameter tuning, training times, and computational costs. Learn about this process here.

Running the model

This model may be run with the transformers library. For accelerated inference with sparsity, deploy with nm-vllm or deepsparse.

# pip install transformers accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("neuralmagic/Llama-2-7b-ultrachat")
model = AutoModelForCausalLM.from_pretrained("neuralmagic/Llama-2-7b-ultrachat", device_map="auto")

input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer.apply_chat_template(input_text, add_generation_prompt=True, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))

Evaluation Benchmark Results

Model evaluation metrics and results.

Benchmark	Metric	Llama-2-7b-ultrachat	Llama-2-7b-pruned50-retrained-ultrachat
MMLU	5-shot, top-1	xxxx	xxxx
HellaSwag	0-shot	xxxx	xxxx
WinoGrande	partial score	xxxx	xxxx
ARC-c		xxxx	xxxx
TruthfulQA	5-shot	xxxx	xxxx
HumanEval	pass@1	xxxx	xxxx
GSM8K	maj@1	xxxx	xxxx

Model Training Details

Coming soon.

Help

For further support, and discussions on these models and AI in general, join Neural Magic's Slack Community

Downloads last month: 12

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for RedHatAI/Llama-2-7b-ultrachat200k

Base model

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

Finetuned

(962)

this model

Quantizations

1 model

Dataset used to train RedHatAI/Llama-2-7b-ultrachat200k

Papers for RedHatAI/Llama-2-7b-ultrachat200k

Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment

Paper • 2405.03594 • Published May 6, 2024 • 7