Instructions to use nitky/AtheneX-V2-72B-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nitky/AtheneX-V2-72B-instruct with Transformers:

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

pipe = pipeline("text-generation", model="nitky/AtheneX-V2-72B-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nitky/AtheneX-V2-72B-instruct")
model = AutoModelForCausalLM.from_pretrained("nitky/AtheneX-V2-72B-instruct", 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 nitky/AtheneX-V2-72B-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nitky/AtheneX-V2-72B-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nitky/AtheneX-V2-72B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nitky/AtheneX-V2-72B-instruct

SGLang

How to use nitky/AtheneX-V2-72B-instruct 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 "nitky/AtheneX-V2-72B-instruct" \
    --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": "nitky/AtheneX-V2-72B-instruct",
		"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 "nitky/AtheneX-V2-72B-instruct" \
        --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": "nitky/AtheneX-V2-72B-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nitky/AtheneX-V2-72B-instruct with Docker Model Runner:
```
docker model run hf.co/nitky/AtheneX-V2-72B-instruct
```

AtheneX-V2-72B-instruct / mergekit_config.yml

nitky

Upload 4 files

4cc7a0b verified almost 2 years ago

Raw

History Blame Contribute Delete

4.52 kB

	merge_method: task_arithmetic
	base_model: Nexusflow/Athene-V2-Agent
	models:
	- model: Nexusflow/Athene-V2-Chat
	parameters:
	weight:
	- filter: embed_tokens
	value: 1.0
	- value: 0
	dtype: bfloat16
	tokenizer_source: Nexusflow/Athene-V2-Agent
	name: Athene-V2-Chat-VE-AA
	---
	merge_method: task_arithmetic
	base_model: Nexusflow/Athene-V2-Agent
	models:
	- model: Qwen/Qwen2.5-72B
	parameters:
	weight:
	- filter: embed_tokens
	value: 1.0
	- value: 0
	dtype: bfloat16
	tokenizer_source: Nexusflow/Athene-V2-Agent
	name: Qwen2.5-72B-VE-AA
	---
	merge_method: task_arithmetic
	base_model: Nexusflow/Athene-V2-Agent
	models:
	- model: Qwen/Qwen2.5-72B-Instruct
	parameters:
	weight:
	- filter: embed_tokens
	value: 1.0
	- value: 0
	dtype: bfloat16
	tokenizer_source: Nexusflow/Athene-V2-Agent
	name: Qwen2.5-72B-Instruct-VE-AA
	---
	merge_method: task_arithmetic
	base_model: Nexusflow/Athene-V2-Agent
	models:
	- model: AXCXEPT/EZO-Qwen2.5-72B-Instruct
	parameters:
	weight:
	- filter: embed_tokens
	value: 1.0
	- value: 0
	dtype: bfloat16
	tokenizer_source: Nexusflow/Athene-V2-Agent
	name: EZO-Qwen2.5-72B-Instruct-VE-AA
	---
	merge_method: task_arithmetic
	base_model: Nexusflow/Athene-V2-Agent
	models:
	- model: EVA-UNIT-01/EVA-Qwen2.5-72B-v0.1
	parameters:
	weight:
	- filter: embed_tokens
	value: 1.0
	- value: 0
	dtype: bfloat16
	tokenizer_source: Nexusflow/Athene-V2-Agent
	name: EVA-Qwen2.5-72B-v0.1-VE-AA
	---
	merge_method: task_arithmetic
	base_model: Nexusflow/Athene-V2-Agent
	models:
	- model: anthracite-org/magnum-v4-72b
	parameters:
	weight:
	- filter: embed_tokens
	value: 1.0
	- value: 0
	dtype: bfloat16
	tokenizer_source: Nexusflow/Athene-V2-Agent
	name: magnum-v4-72b-VE-AA
	---
	merge_method: task_arithmetic
	base_model: Qwen2.5-72B-VE-AA
	models:
	- model: Nexusflow/Athene-V2-Agent
	parameters:
	weight: 1.0
	- model: Athene-V2-Chat-VE-AA
	parameters:
	weight: 0.8
	dtype: bfloat16
	name: AtheneX-V2-72B-instruct-preset-athene-chat
	---
	merge_method: task_arithmetic
	base_model: Qwen2.5-72B-VE-AA
	models:
	- model: Nexusflow/Athene-V2-Agent
	parameters:
	weight: 1.0
	- model: Qwen2.5-72B-Instruct-VE-AA
	parameters:
	weight: 0.8
	dtype: bfloat16
	name: AtheneX-V2-72B-instruct-preset-default
	---
	merge_method: task_arithmetic
	base_model: Qwen2.5-72B-VE-AA
	models:
	- model: Nexusflow/Athene-V2-Agent
	parameters:
	weight: 1.0
	- model: EZO-Qwen2.5-72B-Instruct-VE-AA
	parameters:
	weight: 0.8
	dtype: bfloat16
	name: AtheneX-V2-72B-instruct-preset-ezo
	---
	merge_method: task_arithmetic
	base_model: Qwen2.5-72B-VE-AA
	models:
	- model: Nexusflow/Athene-V2-Agent
	parameters:
	weight: 1.0
	- model: EVA-Qwen2.5-72B-v0.1-VE-AA
	parameters:
	weight: 0.8
	dtype: bfloat16
	name: AtheneX-V2-72B-instruct-preset-eva
	---
	merge_method: task_arithmetic
	base_model: Qwen2.5-72B-VE-AA
	models:
	- model: Nexusflow/Athene-V2-Agent
	parameters:
	weight: 1.0
	- model: magnum-v4-72b-VE-AA
	parameters:
	weight: 0.8
	dtype: bfloat16
	name: AtheneX-V2-72B-instruct-preset-magnum
	---
	merge_method: model_stock
	base_model: Qwen2.5-72B-VE-AA
	models:
	- model: Nexusflow/Athene-V2-Agent
	- model: AtheneX-V2-72B-instruct-preset-athene-chat
	- model: AtheneX-V2-72B-instruct-preset-default
	dtype: bfloat16
	name: AtheneX-V2-72B-instruct-it-alpha
	---
	merge_method: model_stock
	base_model: Qwen2.5-72B-VE-AA
	models:
	- model: Nexusflow/Athene-V2-Agent
	- model: AtheneX-V2-72B-instruct-preset-athene-chat
	- model: AtheneX-V2-72B-instruct-preset-ezo
	dtype: bfloat16
	name: AtheneX-V2-72B-instruct-it-beta
	---
	merge_method: model_stock
	base_model: Qwen2.5-72B-VE-AA
	models:
	- model: Nexusflow/Athene-V2-Agent
	- model: AtheneX-V2-72B-instruct-preset-athene-chat
	- model: AtheneX-V2-72B-instruct-preset-eva
	dtype: bfloat16
	name: AtheneX-V2-72B-instruct-it-gamma
	---
	merge_method: model_stock
	base_model: Qwen2.5-72B-VE-AA
	models:
	- model: Nexusflow/Athene-V2-Agent
	- model: AtheneX-V2-72B-instruct-preset-athene-chat
	- model: AtheneX-V2-72B-instruct-preset-magnum
	dtype: bfloat16
	name: AtheneX-V2-72B-instruct-it-delta
	---
	merge_method: model_stock
	base_model: Qwen2.5-72B-VE-AA
	models:
	- model: AtheneX-V2-72B-instruct-it-alpha
	- model: AtheneX-V2-72B-instruct-it-beta
	- model: AtheneX-V2-72B-instruct-it-gamma
	- model: AtheneX-V2-72B-instruct-it-delta
	dtype: bfloat16
	name: AtheneX-V2-72B-instruct