Instructions to use cookinai/OrcaHermes-Mistral-70B-miqu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cookinai/OrcaHermes-Mistral-70B-miqu with Transformers:

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

pipe = pipeline("text-generation", model="cookinai/OrcaHermes-Mistral-70B-miqu")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cookinai/OrcaHermes-Mistral-70B-miqu")
model = AutoModelForCausalLM.from_pretrained("cookinai/OrcaHermes-Mistral-70B-miqu", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cookinai/OrcaHermes-Mistral-70B-miqu with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cookinai/OrcaHermes-Mistral-70B-miqu"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cookinai/OrcaHermes-Mistral-70B-miqu",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cookinai/OrcaHermes-Mistral-70B-miqu

SGLang

How to use cookinai/OrcaHermes-Mistral-70B-miqu 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 "cookinai/OrcaHermes-Mistral-70B-miqu" \
    --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": "cookinai/OrcaHermes-Mistral-70B-miqu",
		"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 "cookinai/OrcaHermes-Mistral-70B-miqu" \
        --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": "cookinai/OrcaHermes-Mistral-70B-miqu",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cookinai/OrcaHermes-Mistral-70B-miqu with Docker Model Runner:
```
docker model run hf.co/cookinai/OrcaHermes-Mistral-70B-miqu
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OrcaHermes-Mistral-70B

This model was created by SLERP Merging 2 Miqu Models trained on 2 high preforming datsets.

Just an experiment, have not seen much miqu slerps yet.

Models Merged

The following models were included in the merge:

alicecomfy/miqu-openhermes-full

Base Miqu Trained on Openhermes

ShinojiResearch/Senku-70B-Full

Base Miqu Trained on Slimorca

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: local//path//to//Senku-70B-Full
        layer_range: [0, 80]
      - model: local//path//to//miqu-openhermes-full
        layer_range: [0, 80]
merge_method: slerp
base_model: local//path//to//Senku-70B-Full
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: float16

Downloads last month: 55

Safetensors

Model size

69B params

Tensor type

F16

Model tree for cookinai/OrcaHermes-Mistral-70B-miqu

Quantizations

1 model