Downloads · 30 days
8
2% of all-time downloads
Factor168/lfm2-hybridai-iat-sft-merged
lfm2-hybridai-iat-sft-merged is a text generation model from Factor168. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Full merged checkpoint of LiquidAI/LFM2-1.2B fine-tuned (LoRA, merged) on implicit-association prompts from iat/iatfinetunedataset.jsonl using iat/peftfinetuneqwen3.py.
Downloads · 30 days
8
2% of all-time downloads
All-time downloads
524
Public
Parameters
1.2B
2.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.3 GB · 100%
From the Hugging Face model README
Full merged checkpoint of LiquidAI/LFM2-1.2B fine-tuned (LoRA, merged) on implicit-association
prompts from iat/iat_finetune_dataset.jsonl using iat/peft_finetune_qwen3.py.
LiquidAI/LFM2-1.2Bmerge_and_unload)iat/iat_finetune_dataset.jsonlinstruction/input → outputiat/peft_finetune_qwen3.pyWie stark ist die implizite Assoziation zwischen Porsche und Sportlichkeit? → [1, 32903, 16966, 2168, 1277, 16735, 994, 1125, 1783, 1076, 599, 4149, 9844, 59870, 1044, 11499, 25554, 540]Welche impliziten Assoziationen bestehen zwischen Nvidia und KI? → [1, 32617, 1161, 16735, 994, 4180, 1783, 1076, 599, 4149, 771, 55398, 9844, 928, 19153, 972, 1044, 984, 550, 540]Messe die impliziten Assozationen mit OpenAI → [1, 554, 7042, 1277, 16735, 994, 4180, 1783, 1076, 599, 22270, 1821, 8442, 22849]Vergleiche die impliziten Assoziationen mit Volkswagen zwischen Männern und Frauen → [1, 563, 1702, 799, 5837, 1277, 16735, 994, 4180, 1783, 1076, 599, 4149, 771, 1821, 22526, 24532, 9844, 62088, 1343, 1044, 19811]Was sind die impliziten Assoziationen mit Nike? → [1, 28519, 3987, 1277, 16735, 994, 4180, 1783, 1076, 599, 4149, 771, 1821, 57704, 540]Bewerte die implizite Verbindung: Tesla und Autopilot → [1, 543, 1225, 29674, 1277, 16735, 994, 1125, 40838, 535, 44261, 1044, 4669, 53051, 849]import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "Factor168/lfm2-hybridai-iat-sft-merged"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="auto").eval()
prompt = "Was sind die impliziten Assoziationen mit Nike?"
text = tok.apply_chat_template(
[{"role": "user", "content": prompt}],
tokenize=False,
add_generation_prompt=True,
)
inputs = tok(text, return_tensors="pt").to(model.device)
out = model.generate(
**inputs,
max_new_tokens=200,
do_sample=True,
temperature=0.7,
top_p=0.9,
pad_token_id=tok.pad_token_id,
)
print(tok.decode(out[0, inputs['input_ids'].shape[1]:], skip_special_tokens=True))