Instructions to use iamplus/Llama-2-70b-hf-ChatOrca-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iamplus/Llama-2-70b-hf-ChatOrca-v1 with Transformers:

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

pipe = pipeline("text-generation", model="iamplus/Llama-2-70b-hf-ChatOrca-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("iamplus/Llama-2-70b-hf-ChatOrca-v1")
model = AutoModelForCausalLM.from_pretrained("iamplus/Llama-2-70b-hf-ChatOrca-v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use iamplus/Llama-2-70b-hf-ChatOrca-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iamplus/Llama-2-70b-hf-ChatOrca-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iamplus/Llama-2-70b-hf-ChatOrca-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/iamplus/Llama-2-70b-hf-ChatOrca-v1

SGLang

How to use iamplus/Llama-2-70b-hf-ChatOrca-v1 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 "iamplus/Llama-2-70b-hf-ChatOrca-v1" \
    --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": "iamplus/Llama-2-70b-hf-ChatOrca-v1",
		"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 "iamplus/Llama-2-70b-hf-ChatOrca-v1" \
        --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": "iamplus/Llama-2-70b-hf-ChatOrca-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use iamplus/Llama-2-70b-hf-ChatOrca-v1 with Docker Model Runner:
```
docker model run hf.co/iamplus/Llama-2-70b-hf-ChatOrca-v1
```

Description :

This model is trained on a mix of Orca data and Open Source + Closed Multi-turn Conversation data to create a better reasoning model which is capable of holding multi-turn conversations as well.

The Dataset split description, Prompt description as well as Training Parameters are given below.

Prompt Description :

The prompt template for the first turn looks like this:

<s>[INST] <<SYS>>
{{ system_prompt }}
<</SYS>>

{{ user_message }} [/INST]

The prompt template for the multi-turn conversation looks like this:

<s>[INST] <<SYS>>
{{ system_prompt }}
<</SYS>>

{{ user_msg_1 }} [/INST] {{ model_answer_1 }} </s><s>[INST] {{ user_msg_2 }} [/INST]

This model follows the official Meta's chat model Prompt format. Please refer here : https://huggingface.co/blog/llama2#how-to-prompt-llama-2 on how to prompt the model for single/multi-turn conversations.

Base model : meta-llama/Llama-2-70b-hf

Data :

1M Orca dara (Gpt-4 Orca data - OpenOrca)
1.7M chat data (includes OpenAssistant Chat data, Ultrachat, and many more open source Chat Datasets)
30k OpenPlatypus data

Training Params :

Number of Epochs : 1
Batch Size : 64
Sequence Length : 4096
Learning Rate : 2e-5 (Cosine)
Weight Decay : 0.1
Gradient Clipping : 1.0
Gamma : 0.85
beta_1 : 0.9
beta_2 : 0.95
eps : 1e-5
Precision : bf16
Optimizer : Any Precision AdamW Optimizer

Downloads last month: 3

Safetensors

Model size

69B params

Tensor type

F16

iamplus
/

Llama-2-70b-hf-ChatOrca-v1

Datasets used to train iamplus/Llama-2-70b-hf-ChatOrca-v1