Instructions to use SEE7/Astheral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SEE7/Astheral with Transformers:

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

pipe = pipeline("text-generation", model="SEE7/Astheral")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SEE7/Astheral")
model = AutoModelForCausalLM.from_pretrained("SEE7/Astheral", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SEE7/Astheral with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SEE7/Astheral"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SEE7/Astheral",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SEE7/Astheral

SGLang

How to use SEE7/Astheral 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 "SEE7/Astheral" \
    --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": "SEE7/Astheral",
		"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 "SEE7/Astheral" \
        --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": "SEE7/Astheral",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SEE7/Astheral with Docker Model Runner:
```
docker model run hf.co/SEE7/Astheral
```

Astheral

File size: 2,013 Bytes

c9089df

{
  "status": "complete",
  "deployed_weight_revision": "37adef9b3917e4a3de0bb77f0db71089b7b82202",
  "expanded_candidate_revision": "4304e2898cd3e864be4a0787ebd7f37a0189229f",
  "candidate_branch": "v3-expanded-20261113",
  "trainable_parameters": 83886080,
  "optimizer_steps": 360,
  "training_runtime_seconds": 822.6722,
  "baseline_standard_acc": {
    "arc_easy": 0.87,
    "piqa": 0.79,
    "sciq": 0.94,
    "winogrande": 0.79
  },
  "expanded_standard_results": {
    "arc_easy": {
      "name": "arc_easy",
      "alias": "arc_easy",
      "sample_len": 100,
      "acc,none": 0.86,
      "acc_stderr,none": 0.03487350880197771,
      "acc_norm,none": 0.89,
      "acc_norm_stderr,none": 0.03144660377352203
    },
    "piqa": {
      "name": "piqa",
      "alias": "piqa",
      "sample_len": 100,
      "acc,none": 0.8,
      "acc_stderr,none": 0.04020151261036845,
      "acc_norm,none": 0.84,
      "acc_norm_stderr,none": 0.03684529491774711
    },
    "sciq": {
      "name": "sciq",
      "alias": "sciq",
      "sample_len": 100,
      "acc,none": 0.94,
      "acc_stderr,none": 0.02386832565759419,
      "acc_norm,none": 0.96,
      "acc_norm_stderr,none": 0.019694638556693237
    },
    "winogrande": {
      "name": "winogrande",
      "alias": "winogrande",
      "sample_len": 100,
      "acc,none": 0.79,
      "acc_stderr,none": 0.04093601807403326
    }
  },
  "standard_sample_count_per_task": 100,
  "baseline_bf16_task_suite": 43,
  "expanded_bf16_task_suite": 43,
  "decision": "Retain existing V3 weights: no aggregate benchmark gain or BF16 task-suite gain. Expanded weights remain available on candidate branch.",
  "precision_note": "The training script gate compares quantized baseline with BF16 candidate. Final release decision instead uses previously measured BF1643/60 and identical standard benchmark settings.",
  "output_cap": 4096,
  "default_output_tokens": 1024,
  "generation_time_seconds": 110,
  "zerogpu_allocation_seconds": 120,
  "quota_reserve_seconds": 180
}