Instructions to use intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal with Transformers:

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

pipe = pipeline("text-generation", model="intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal")
model = AutoModelForCausalLM.from_pretrained("intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal

SGLang

How to use intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal 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 "intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal with Docker Model Runner:
```
docker model run hf.co/intervitens-archive/Nous-Hermes-2-Mixtral-8x7B-DPO-3.7bpw-h6-exl2-rpcal
```

intervitens commited on Jan 16, 2024

Commit

ce31f28

verified ·

1 Parent(s): f076bc1

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -0

README.md CHANGED Viewed

@@ -18,6 +18,16 @@ language:
 - en
 ---
 # Nous Hermes 2 - Mixtral 8x7B - DPO
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/btRmXWMG7PXatTs-u3G85.jpeg)

 - en
 ---
+Quantized using 200 samples of 8192 tokens from an RP-oriented [PIPPA](https://huggingface.co/datasets/royallab/PIPPA-cleaned) dataset. For purposes other than RP, use quantizations done on a more general dataset.
+Requires ExllamaV2 version 0.0.11 and up.
+Original model link: [NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO)
+Original model README below.
+***
 # Nous Hermes 2 - Mixtral 8x7B - DPO
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/btRmXWMG7PXatTs-u3G85.jpeg)