Bachstelze/smolSynformerPeft

SmolSynformer: SmolLM2 as Syntax-aware transformer

This is a adapter version with slightly less capabilities than the full SFT smolSynformer model.

Inference with transformer

from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig, pipeline

test_model = "Bachstelze/smolSynformerPeft"
model = AutoModelForCausalLM.from_pretrained(test_model)
tokenizer = AutoTokenizer.from_pretrained(test_model)
config = AutoConfig.from_pretrained(test_model)

prompt_pipeline = pipeline("text-generation", model=test_model, tokenizer=tokenizer, max_new_tokens=250)
print(prompt_pipeline("Why is syntax relevant for language modeling and instruction following?\n"))

Example answer:

Syntax is relevant for language modeling and instruction following because it is the language that is being modeled. The language is the language that is being taught. The language is the language that is being used in the instruction. Therefore, the language that is being taught is the language that is being modeled.