Instructions to use alicecomfy/miqu-openhermes-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alicecomfy/miqu-openhermes-full with Transformers:

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

pipe = pipeline("text-generation", model="alicecomfy/miqu-openhermes-full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alicecomfy/miqu-openhermes-full")
model = AutoModelForCausalLM.from_pretrained("alicecomfy/miqu-openhermes-full")
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

vLLM

How to use alicecomfy/miqu-openhermes-full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alicecomfy/miqu-openhermes-full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alicecomfy/miqu-openhermes-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alicecomfy/miqu-openhermes-full

SGLang

How to use alicecomfy/miqu-openhermes-full 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 "alicecomfy/miqu-openhermes-full" \
    --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": "alicecomfy/miqu-openhermes-full",
		"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 "alicecomfy/miqu-openhermes-full" \
        --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": "alicecomfy/miqu-openhermes-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use alicecomfy/miqu-openhermes-full with Docker Model Runner:
```
docker model run hf.co/alicecomfy/miqu-openhermes-full
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

lora merge as it was really tricky to get it to work of https://huggingface.co/152334H/miqu-1-70b-hermes2.5-qlora.

Base Model: Miqu 70B (Mistral AI Leak) Dequantized by 152234h Finetune also by 152234h

Outputs seem good, but the prompting is still a bit buggy, not sure if that's an error on my part.

For me it wouldn't generate text until I activated flash attention 2 in Oogabooga. You need around 130 GB vram, 2 a100 80 or h100 work, as does 6 3090 or 4090.

Downloads last month: 4

Safetensors

Model size

69B params

Tensor type

F16

Model tree for alicecomfy/miqu-openhermes-full

Quantizations

2 models