Instructions to use aayanmishra-ml/Athena-R3-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aayanmishra-ml/Athena-R3-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="aayanmishra-ml/Athena-R3-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aayanmishra-ml/Athena-R3-1.5B")
model = AutoModelForCausalLM.from_pretrained("aayanmishra-ml/Athena-R3-1.5B")
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 aayanmishra-ml/Athena-R3-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aayanmishra-ml/Athena-R3-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aayanmishra-ml/Athena-R3-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aayanmishra-ml/Athena-R3-1.5B

SGLang

How to use aayanmishra-ml/Athena-R3-1.5B 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 "aayanmishra-ml/Athena-R3-1.5B" \
    --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": "aayanmishra-ml/Athena-R3-1.5B",
		"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 "aayanmishra-ml/Athena-R3-1.5B" \
        --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": "aayanmishra-ml/Athena-R3-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use aayanmishra-ml/Athena-R3-1.5B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for aayanmishra-ml/Athena-R3-1.5B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for aayanmishra-ml/Athena-R3-1.5B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aayanmishra-ml/Athena-R3-1.5B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="aayanmishra-ml/Athena-R3-1.5B",
    max_seq_length=2048,
)

Docker Model Runner
How to use aayanmishra-ml/Athena-R3-1.5B with Docker Model Runner:
```
docker model run hf.co/aayanmishra-ml/Athena-R3-1.5B
```

Aayan Mishra commited on Jan 28, 2025

Commit

115893a

verified ·

1 Parent(s): b8addaf

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -14

README.md CHANGED Viewed

@@ -58,20 +58,18 @@ library_name: transformers
 ---
 # **Evaluation**
-Below are the evaluations of the Atlas-Pro models and Deepseek's R1 Qwen Distills (The model that started the whole Atlas family) and some ather simillar models:
-| **Metric**              | **Spestly Atlas Pro (7B)** | **Spestly Atlas Pro (1.5B)** | DeepSeek-R1-Distill-Qwen (7B) | DeepSeek-R1-Distill-Qwen (1.5B) | mistralai/Mistral-7B-Instruct-v0.3 |
-|-------------------------|---------------------------|------------------------------|-----------------------------------|-------------------------------------|-------------------------------------|
-| **Average**             | **22.65%**               | 12.93%                       | 11.73%                            | 7.53%                              | 19.17%                                |
-| **IFEval**              | 31.54%                   | 24.30%                       | 40.38%                        | 34.63%                             | **54.65%**                                |
-| **BBH**                 | 25.27%               | 9.08%                        | 7.88%                             | 4.73%                              | **25.57%**                                |
-| **MATH**                | **38.90%**               | 25.83%                       | 0.00%                             | 0.00%                              | 3.55%                                 |
-| **GPQA**                | **11.63%**               | 6.26%                        | 3.91%                             | 2.97%                              | 3.91%                                 |
-| **MUSR**                | **6.65%**                | 1.86%                        | 3.55%                             | 2.08%                              | 4.30%                                 |
-| **MMLU-Pro**            | 21.89%               | 10.28%                       | 14.68%                            | 0.78%                              | **23.06%**                                |
-| **Carbon Emissions (kg)** | 0.69 kg                  | 0.59 kg                  | 0.68 kg                           | 0.62 kg                             | **0.54 kg**                            |
-| **Parameters**          | ~7B                       | ~1.5B                       | ~7B                               | ~1.5B                               | ~7B                                  |

 ---
 # **Evaluation**
+Below are the evaluations of the Atlas-Pro models and Deepseek's R1 Qwen Distills (The model that started the whole Atlas family):
+| **Metric**              | **Spestly Atlas Pro (7B)** | **Spestly Atlas Pro (1.5B)** | DeepSeek-R1-Distill-Qwen (7B) | DeepSeek-R1-Distill-Qwen (1.5B) |
+|-------------------------|---------------------------|------------------------------|-----------------------------------|-------------------------------------|
+| **Average**             | **22.65%**               | 12.93%                       | 11.73%                            | 7.53%                              |
+| **IFEval**              | 31.54%                   | 24.30%                       | **40.38%**                        | 34.63%                             |
+| **BBH**                 | **25.27%**               | 9.08%                        | 7.88%                             | 4.73%                              |
+| **MATH**                | **38.90%**               | 25.83%                       | 0.00%                             | 0.00%                              |
+| **GPQA**                | **11.63%**               | 6.26%                        | 3.91%                             | 2.97%                              |
+| **MUSR**                | **6.65%**                | 1.86%                        | 3.55%                             | 2.08%                              |
+| **MMLU-Pro**            | **21.89%**               | 10.28%                       | 14.68%                            | 0.78%                              |
+| **Carbon Emissions (kg)** | 0.69 kg                  | **0.59 kg**                  | 0.68 kg                           | 0.62 kg                             |