Text Generation
Transformers
Safetensors
English
llama
astheral
instruct
qlora
conversational
text-generation-inference
Instructions to use SEE7/Astheral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
Download evaluation.json from SEE7/Astheral: direct link, hf CLI and curl.
- Browser
- Download file 2.41 kB
-
https://huggingface.co/SEE7/Astheral/resolve/main/evaluation.json
- Command line
-
hf download hf://SEE7/Astheral/evaluation.json
-
curl -L -o evaluation.json https://huggingface.co/SEE7/Astheral/resolve/main/evaluation.json
2.41 kB
| { | |
| "version": "3", | |
| "training": { | |
| "status": "complete", | |
| "parent_revision": "d9aa899722be4788f57107c2951c72d0ec6614ee", | |
| "hardware": "NVIDIA A10G", | |
| "job_timeout_seconds": 5400, | |
| "listed_usd_per_hour": 1.0, | |
| "training_seed": 20261113, | |
| "baseline_passed": 40, | |
| "elapsed_seconds": 622.09, | |
| "training_examples": 1713, | |
| "trainable_parameters": 41943040, | |
| "training": { | |
| "train_runtime": 390.2404, | |
| "train_samples_per_second": 1.845, | |
| "train_steps_per_second": 0.461, | |
| "total_flos": 3960249019342848.0, | |
| "train_loss": 0.2867420093880759, | |
| "epoch": 0.4203152364273205 | |
| }, | |
| "optimizer_steps": 180, | |
| "candidate_passed": 49, | |
| "reloaded_passed": 43, | |
| "groups": { | |
| "integer": { | |
| "baseline": 0, | |
| "candidate": 3, | |
| "total": 20 | |
| }, | |
| "exact": { | |
| "baseline": 20, | |
| "candidate": 20, | |
| "total": 20 | |
| }, | |
| "code": { | |
| "baseline": 10, | |
| "candidate": 10, | |
| "total": 10 | |
| }, | |
| "json": { | |
| "baseline": 10, | |
| "candidate": 10, | |
| "total": 10 | |
| } | |
| }, | |
| "quality_gate_passed": true, | |
| "peak_gpu_bytes": 18991949312 | |
| }, | |
| "matched_bf16_and_independent_tests": { | |
| "comparison": "V2 versus V3, both BF16", | |
| "v2_revision": "d9aa899722be4788f57107c2951c72d0ec6614ee", | |
| "paired_bf16_scores": { | |
| "base": 41, | |
| "astheral": 43 | |
| }, | |
| "suite": "GSM8K test rows 231-238; HumanEval selected tasks 0,3,7,12,18,25,36,45", | |
| "scores": { | |
| "base": { | |
| "code": { | |
| "passed": 6, | |
| "total": 8, | |
| "token_limited": 0 | |
| }, | |
| "number": { | |
| "passed": 6, | |
| "total": 8, | |
| "token_limited": 0 | |
| } | |
| }, | |
| "astheral": { | |
| "code": { | |
| "passed": 6, | |
| "total": 8, | |
| "token_limited": 0 | |
| }, | |
| "number": { | |
| "passed": 6, | |
| "total": 8, | |
| "token_limited": 0 | |
| } | |
| } | |
| }, | |
| "no_material_regression_gate": true, | |
| "astheral_revision": "8d553fe747fd6e12fd650c97b712e7009a8b4f9e", | |
| "settings": { | |
| "sampling": false, | |
| "code_max_new_tokens": 768, | |
| "math_max_new_tokens": 1536 | |
| }, | |
| "hardware": "NVIDIA A10G", | |
| "source_revisions": { | |
| "gsm8k": "740312add88f781978c0658806c59bc2815b9866", | |
| "humaneval": "7dce6050a7d6d172f3cc5c32aa97f52fa1a2e544" | |
| } | |
| } | |
| } |