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", 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 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
```

leafspark commited on Aug 14, 2024

Commit

f281f2a

verified ·

1 Parent(s): adde290

model: update model card and specs

Browse files

Files changed (1) hide show

README.md +11 -7

README.md CHANGED Viewed

@@ -1,5 +1,5 @@
 ---
-license: unknown
 pipeline_tag: text-generation
 language:
 - en
@@ -23,15 +23,16 @@ FeatherQwen is a 72B parameter language model created through a merge of Qwen2-7
 ## Technical Specifications
 ### Architecture
 - Models: Qwen2-72B-Instruct (base), calme2.1-72b, magnum-72b-v1
-- Merged layers: 79
 - Total tensors: 1,043
 ### Tensor Distribution
-- Attention layers: 333 files
-- MLP layers: 333 files
-- Layer norms: 166 files
-- Miscellaneous (embeddings, output): 211 files
 ### Merging
 Custom script utilizing safetensors library.
@@ -47,8 +48,11 @@ model = AutoModelForCausalLM.from_pretrained("leafspark/FeatherQwen2-72B-v0.1",
                                              device_map="auto",
                                              torch_dtype=torch.float16)
 tokenizer = AutoTokenizer.from_pretrained("leafspark/FeatherQwen2-72B-v0.1")
 ```
 ### Hardware Requirements
 - Minimum ~140GB of storage

 ---
+license: other
 pipeline_tag: text-generation
 language:
 - en
 ## Technical Specifications
 ### Architecture
+- `Qwen2ForCasualLM`
 - Models: Qwen2-72B-Instruct (base), calme2.1-72b, magnum-72b-v1
+- Merged layers: 80
 - Total tensors: 1,043
 ### Tensor Distribution
+- Attention layers: 560 files
+- MLP layers: 240 files
+- Layer norms: 160 files
+- Miscellaneous (embeddings, output): 83 files
 ### Merging
 Custom script utilizing safetensors library.
                                              device_map="auto",
                                              torch_dtype=torch.float16)
 tokenizer = AutoTokenizer.from_pretrained("leafspark/FeatherQwen2-72B-v0.1")
 ```
+### GGUFs
+Find them here: [leafspark/FeatherQwen2-72B-v0.1-GGUF](https://huggingface.co/leafspark/FeatherQwen2-72B-v0.1-GGUF)
 ### Hardware Requirements
 - Minimum ~140GB of storage