How to use from the
Use from the
Transformers library
# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Sakalti/Saba1.5-1.5B")
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("Sakalti/Saba1.5-1.5B")
model = AutoModelForCausalLM.from_pretrained("Sakalti/Saba1.5-1.5B", 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]:]))
Quick Links

Uploaded model

  • Developed by: Sakalti
  • License: apache2.0
  • Finetuned from model : Sakalti/Saba1-1.8B This qwen model was trained 2x faster with Unsloth and Huggingface's TRL library.

This models was using "kunishou/databricks-dolly-15k-ja" This dataset is licensed under CC BY SA 3.0

Last Update : 2023-05-28 paramaters(no embedding layer) 1.31B paramaters(yes embedding layer) 1.54B layers: 28layers

概要

Saba1.5はSaba1をフゑむンチγƒ₯γƒΌγƒ‹γƒ³γ‚°γ—γŸγƒ’γƒ‡γƒ«γ§γ™γ€‚ ζ€§θƒ½γ―γΎγ γ‚γ‹γ‚ŠγΎγ›γ‚“γŒδΈŠζ˜‡γ—γ¦γ‚‹γ§γ—γ‚‡γ†γ€‚

Downloads last month
71
Safetensors
Model size
2B params
Tensor type
F16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for Sakalti/Saba1.5-1.5B

Finetunes
1 model
Merges
3 models
Quantizations
2 models

Collection including Sakalti/Saba1.5-1.5B