GLM4.7-Distill-LFM2.5-1.2B

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

model_id = "yasserrmd/GLM4.7-Distill-LFM2.5-1.2B"

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    dtype="bfloat16",
    # attn_implementation="flash_attention_2"  # uncomment on compatible GPU
)

tokenizer = AutoTokenizer.from_pretrained(model_id)
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

prompt = "Implement QuickSort algorithm with complexity analysis"

input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
).to(model.device)

output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.1,
    top_k=50,
    top_p=0.1,
    repetition_penalty=1.05,
    max_new_tokens=512,
    streamer=streamer,
)