Instructions to use jordiclive/Llama-2-70b-oasst-1-200 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jordiclive/Llama-2-70b-oasst-1-200 with Transformers:

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

pipe = pipeline("text-generation", model="jordiclive/Llama-2-70b-oasst-1-200")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jordiclive/Llama-2-70b-oasst-1-200")
model = AutoModelForCausalLM.from_pretrained("jordiclive/Llama-2-70b-oasst-1-200")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jordiclive/Llama-2-70b-oasst-1-200 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jordiclive/Llama-2-70b-oasst-1-200"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jordiclive/Llama-2-70b-oasst-1-200",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jordiclive/Llama-2-70b-oasst-1-200

SGLang

How to use jordiclive/Llama-2-70b-oasst-1-200 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 "jordiclive/Llama-2-70b-oasst-1-200" \
    --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": "jordiclive/Llama-2-70b-oasst-1-200",
		"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 "jordiclive/Llama-2-70b-oasst-1-200" \
        --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": "jordiclive/Llama-2-70b-oasst-1-200",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jordiclive/Llama-2-70b-oasst-1-200 with Docker Model Runner:
```
docker model run hf.co/jordiclive/Llama-2-70b-oasst-1-200
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Open-Assistant Llama2 70B SFT OASST

This model is a fine-tuning of Llama2 70B LLM. It was trained on a mixture of OASST top-1 threads.

Model Details

Finetuned from: Llama2 70B
Model type: Causal decoder-only transformer language model
Language: English, German, Spanish, French (and limited capabilities in Italian, Portuguese, Polish, Dutch, Romanian, Czech, Swedish);
License: Apache 2.0
Contact: Open-Assistant Discord

Prompting

Two special tokens are used to mark the beginning of user and assistant turns: <|prompter|> and <|assistant|>. Each turn ends with a </s> token.

Input prompt example:

<|prompter|>What is a meme, and what's the history behind this word?</s><|assistant|>

The input ends with the <|assistant|> token to signal that the model should start generating the assistant reply.

Citation

@misc{jordiclive_llama2_70b_oasst_1_200,
  title={{Open-Assistant Llama2 70B SFT OASST}},
  author={{Jordan Clive}},
  howpublished={\url{https://huggingface.co/jordiclive/Llama-2-70b-oasst-1-200}},
  year={2023},
  note={Apache 2.0 License. Finetuned on OASST top-1 threads. Languages supported: English, German, Spanish, French.},
  url={https://huggingface.co/jordiclive/Llama-2-70b-oasst-1-200},
}

Downloads last month: 909

Model tree for jordiclive/Llama-2-70b-oasst-1-200

Finetunes

1 model

Quantizations

3 models

jordiclive
/

Llama-2-70b-oasst-1-200

Open-Assistant Llama2 70B SFT OASST

Model Details

Prompting

Citation

Model tree for jordiclive/Llama-2-70b-oasst-1-200

Dataset used to train jordiclive/Llama-2-70b-oasst-1-200

Spaces using jordiclive/Llama-2-70b-oasst-1-200 31