Instructions to use Norquinal/llama-2-7b-claude-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Norquinal/llama-2-7b-claude-chat with Transformers:

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

pipe = pipeline("text-generation", model="Norquinal/llama-2-7b-claude-chat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Norquinal/llama-2-7b-claude-chat")
model = AutoModelForCausalLM.from_pretrained("Norquinal/llama-2-7b-claude-chat", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Norquinal/llama-2-7b-claude-chat with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Norquinal/llama-2-7b-claude-chat

SGLang

How to use Norquinal/llama-2-7b-claude-chat 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 "Norquinal/llama-2-7b-claude-chat" \
    --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": "Norquinal/llama-2-7b-claude-chat",
		"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 "Norquinal/llama-2-7b-claude-chat" \
        --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": "Norquinal/llama-2-7b-claude-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Norquinal/llama-2-7b-claude-chat with Docker Model Runner:
```
docker model run hf.co/Norquinal/llama-2-7b-claude-chat
```

Norquinal commited on Aug 11, 2023

Commit

dd270b1

1 Parent(s): 080ac77

Create README.md

Browse files

Files changed (1) hide show

README.md +27 -0

README.md ADDED Viewed

	@@ -0,0 +1,27 @@

+---
+datasets:
+- Norquinal/claude_multiround_chat_1k
+---
+This is a [LLaMA-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) model fine-tuned using QLoRA (4-bit precision) on my [claude_multiround_chat_1k](https://huggingface.co/datasets/Norquinal/claude_multiround_chat_1k) dataset, which is a randomized subset of ~1000 samples from my [claude_multiround_chat_30k](https://huggingface.co/datasets/Norquinal/claude_multiround_chat_30k) dataset.
+Do not take this model very seriously, it is probably not very good. I haven't a clue of what I'm doing. I just thought it was a fun thing to make.
+## Prompt Format
+The model was finetuned with the Vicuna 1.1 prompt format:
+```
+A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
+USER: {instruction}
+ASSISTANT:
+```
+## Example Usage
+>USER: Write a promotional advertisement for Europa Universalis IV.
+>ASSISTANT: Europa Universalis IV is the latest installment in Paradox Interactive's award-winning strategy game series that takes you on a journey through history from 1492 to 1830. With over 650 nations spanning six continents, Europa Universalis IV offers unparalleled depth of choice with its realistic simulation of world affairs.
+>
+>As ruler of your nation, you will have control over diplomacy, trade, exploration, warfare, religion and more as you strive to build up your empire into one of global dominance. Experience epic battles across land and sea, wage wars against rival powers or ally yourself together to form great coalitions - all while managing resources like food production, gold mining and technological research.
+>
+>With hundreds of events based on actual historical figures and major turning points throughout human civilization, every decision has consequences that shape how history unfolds around you. Will you become a mighty emperor who conquers vast territories? Or a wise leader who builds lasting peace among neighboring kingdoms? Whatever path you choose, Europa Universalis IV provides limitless possibilities for players seeking immersion within their own personal vision of history.
+>
+>So step back in time today and take charge of Europe, Asia or Africa! Build your legacy by shaping the course of history itself in this captivating grand strategy experience unlike any other.