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 / expanded-evaluation /training_report.json

SEE7

Finish V3: document extra rank32 training, standard benchmarks and release decision

c9089df verified 2 days ago

Raw History Blame Contribute Delete

1.06 kB

{
  "status": "complete",
  "parent_revision": "37adef9b3917e4a3de0bb77f0db71089b7b82202",
  "hardware": "NVIDIA A10G",
  "job_timeout_seconds": 5400,
  "listed_usd_per_hour": 1.0,
  "training_seed": 20261113,
  "baseline_passed": 44,
  "elapsed_seconds": 1081.96,
  "training_examples": 1760,
  "trainable_parameters": 83886080,
  "training": {
    "train_runtime": 822.6722,
    "train_samples_per_second": 1.75,
    "train_steps_per_second": 0.438,
    "total_flos": 5294561485455360.0,
    "train_loss": 0.21725553472836812,
    "epoch": 0.8181818181818182
  },
  "optimizer_steps": 360,
  "candidate_passed": 49,
  "reloaded_passed": 43,
  "groups": {
    "exact": {
      "baseline": 20,
      "candidate": 20,
      "total": 20
    },
    "json": {
      "baseline": 10,
      "candidate": 10,
      "total": 10
    },
    "integer": {
      "baseline": 4,
      "candidate": 3,
      "total": 20
    },
    "code": {
      "baseline": 10,
      "candidate": 10,
      "total": 10
    }
  },
  "quality_gate_passed": false,
  "peak_gpu_bytes": 19167454720
}

	{
	"status": "complete",
	"parent_revision": "37adef9b3917e4a3de0bb77f0db71089b7b82202",
	"hardware": "NVIDIA A10G",
	"job_timeout_seconds": 5400,
	"listed_usd_per_hour": 1.0,
	"training_seed": 20261113,
	"baseline_passed": 44,
	"elapsed_seconds": 1081.96,
	"training_examples": 1760,
	"trainable_parameters": 83886080,
	"training": {
	"train_runtime": 822.6722,
	"train_samples_per_second": 1.75,
	"train_steps_per_second": 0.438,
	"total_flos": 5294561485455360.0,
	"train_loss": 0.21725553472836812,
	"epoch": 0.8181818181818182
	},
	"optimizer_steps": 360,
	"candidate_passed": 49,
	"reloaded_passed": 43,
	"groups": {
	"exact": {
	"baseline": 20,
	"candidate": 20,
	"total": 20
	},
	"json": {
	"baseline": 10,
	"candidate": 10,
	"total": 10
	},
	"integer": {
	"baseline": 4,
	"candidate": 3,
	"total": 20
	},
	"code": {
	"baseline": 10,
	"candidate": 10,
	"total": 10
	}
	},
	"quality_gate_passed": false,
	"peak_gpu_bytes": 19167454720
	}