177e1567eb8fb97c77c6ca80393483bb4abe83c8c126a39372b923c86eae5b92

README.md

@@ -60,7 +60,7 @@ You can run the smashed model with these steps:
     ```python 
    from transformers import AutoModelForCausalLM, AutoTokenizer
 
-    model = AutoModelForCausalLM.from_pretrained("PrunaAI/huggyllama-llama-7b-BNB-4bit-smashed",
+    model = AutoModelForCausalLM.from_pretrained("PrunaAI/huggyllama-llama-7b-bnb-4bit-smashed",
                                                  trust_remote_code=True, device_map='auto')
     tokenizer = AutoTokenizer.from_pretrained("huggyllama/llama-7b")
     

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/tmp/tmp1uz1w2ly",
+  "_name_or_path": "/tmp/tmpb4y27ufo",
   "architectures": [
     "LlamaForCausalLM"
   ],

smash_config.json

@@ -8,7 +8,7 @@
         "compilers": "None",
         "task": "text_text_generation",
         "device": "cuda",
-        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsad2ktlzw",
+        "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsy3nu9jue",
         "batch_size": 1,
         "n_quantization_bits": 4,
         "tokenizer": "LlamaTokenizerFast(name_or_path='huggyllama/llama-7b', vocab_size=32000, model_max_length=2048, is_fast=True, padding_side='left', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '<unk>'}, clean_up_tokenization_spaces=False),  added_tokens_decoder={\n\t0: AddedToken(\"<unk>\", rstrip=False, lstrip=False, single_word=False, normalized=True, special=True),\n\t1: AddedToken(\"<s>\", 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}",