f274e274104efd1a07b6d00e4cfdf9ad8a2c1086e3a9a600d91184ba898a734a

README.md

@@ -59,6 +59,8 @@ You can run the smashed model with these steps:
 2. Load & run the model.
     ```python 
    from transformers import AutoModelForCausalLM, AutoTokenizer
+        from hqq.engine.hf import HQQModelForCausalLM
+  from hqq.models.hf.base import AutoHQQHFModel
 
     try:
      model = HQQModelForCausalLM.from_quantized("PrunaAI/facebook-opt-125m-HQQ-1bit-smashed", device_map='auto')

smash_config.json

@@ -14,7 +14,7 @@
         "controlnet": "None",
         "unet_dim": 4,
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsiz5iogt8",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelslpb8rwvi",
         "batch_size": 1,
         "tokenizer": "GPT2TokenizerFast(name_or_path='facebook/opt-125m', vocab_size=50265, model_max_length=1000000000000000019884624838656, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '</s>', 'eos_token': '</s>', 'unk_token': '</s>', 'pad_token': '<pad>'}, clean_up_tokenization_spaces=True),  added_tokens_decoder={\n\t1: AddedToken(\"<pad>\", rstrip=False, lstrip=False, single_word=False, normalized=True, special=True),\n\t2: AddedToken(\"</s>\", rstrip=False, lstrip=False, single_word=False, normalized=True, special=True),\n}",
         "task": "text_text_generation",