Instructions to use Infinimol/miiqu-f16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Infinimol/miiqu-f16 with Transformers:

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

pipe = pipeline("text-generation", model="Infinimol/miiqu-f16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Infinimol/miiqu-f16")
model = AutoModelForCausalLM.from_pretrained("Infinimol/miiqu-f16")
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 Infinimol/miiqu-f16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Infinimol/miiqu-f16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Infinimol/miiqu-f16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Infinimol/miiqu-f16

SGLang

How to use Infinimol/miiqu-f16 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 "Infinimol/miiqu-f16" \
    --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": "Infinimol/miiqu-f16",
		"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 "Infinimol/miiqu-f16" \
        --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": "Infinimol/miiqu-f16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Infinimol/miiqu-f16 with Docker Model Runner:
```
docker model run hf.co/Infinimol/miiqu-f16
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

miiqu-105b-v1.0

Developed by Infinimol AI GmbH

Also Available:

GGUF: Q4_K_M
EXL2: 5.0bpw

8th place on EQ-Bench, beating Qwen1.5-72B-Chat, miqudev/miqu-1-70b, mistral-medium and claude-3-sonnet-20240229. All without fine-tuning or additional training.

Thanks for support from: turboderp, silphendio, sqrkl, and ngxson!

Model Details

Max Context: 32768 tokens
Layers: 105

Prompt template: ChatML or Mistral

chatml:

<|im_start|><|user|>\n<|user-message|><|im_end|>\n<|im_start|><|bot|>\n<|bot-message|><|im_end|>\n

mistral:

[INST] <|user|><|user-message|>[/INST]<|bot|><|bot-message|></s>

Downloads last month: 90

Safetensors

Model size

90B params

Tensor type

F16

Model tree for Infinimol/miiqu-f16

Quantizations

2 models