Instructions to use leafspark/Iridium-72B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leafspark/Iridium-72B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="leafspark/Iridium-72B-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("leafspark/Iridium-72B-v0.1")
model = AutoModelForCausalLM.from_pretrained("leafspark/Iridium-72B-v0.1")
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 leafspark/Iridium-72B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leafspark/Iridium-72B-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leafspark/Iridium-72B-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/leafspark/Iridium-72B-v0.1

SGLang

How to use leafspark/Iridium-72B-v0.1 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 "leafspark/Iridium-72B-v0.1" \
    --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": "leafspark/Iridium-72B-v0.1",
		"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 "leafspark/Iridium-72B-v0.1" \
        --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": "leafspark/Iridium-72B-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use leafspark/Iridium-72B-v0.1 with Docker Model Runner:
```
docker model run hf.co/leafspark/Iridium-72B-v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Iridium-72B-v0.1

Model Description

Iridium is a 72B parameter language model created through a merge of Qwen2-72B-Instruct, calme2.1-72b, and magnum-72b-v1 using model_stock.

Features

72 billion parameters
Combines Magnum prose with Calam smarts

Technical Specifications

Architecture

Qwen2ForCasualLM
Models: Qwen2-72B-Instruct (base), calme2.1-72b, magnum-72b-v1
Merged layers: 80
Total tensors: 963
Context length: 128k

Tensor Distribution

Attention layers: 560 files
MLP layers: 240 files
Layer norms: 160 files
Miscellaneous (embeddings, output): 3 files

Merging

Custom script utilizing safetensors library.

Usage

Loading the Model

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained("leafspark/Iridium-72B-v0.1", 
                                             device_map="auto", 
                                             torch_dtype=torch.float16)
tokenizer = AutoTokenizer.from_pretrained("leafspark/Iridium-72B-v0.1")

GGUFs

Find them here: leafspark/Iridium-72B-v0.1-GGUF

Optimal Sampling Parameters

I found these to work well:

{
  "temperature": 1
  "min_p": 0.08
  "top_p": 1
  "top_k": 40
  "repetition_penalty": 1
}

Hardware Requirements

At least 135GB of free space
~140GB VRAM/RAM

Downloads last month: 2

Safetensors

Model size

73B params

Tensor type

BF16

Model tree for leafspark/Iridium-72B-v0.1

Quantizations

3 models

Collection including leafspark/Iridium-72B-v0.1

Qwen2 Models and Merges

Collection

roleplay+unslopped LLMs, plus Qwen2ForCasualLM -> LlamaForCasualLM conversions • 3 items • Updated Aug 15, 2024