bump(transformers): use upstream implementation

README.md

@@ -34,7 +34,6 @@ tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-2-12b")
 model = AutoModelForCausalLM.from_pretrained(
   "stabilityai/stablelm-2-12b",
   torch_dtype="auto",
-  trust_remote_code=True
 )
 model.cuda()
 inputs = tokenizer("The weather is always wonderful", return_tensors="pt").to(model.device)
@@ -60,7 +59,6 @@ model = AutoModelForCausalLM.from_pretrained(
   "stabilityai/stablelm-2-12b",
   torch_dtype="auto",
   attn_implementation="flash_attention_2",
-  trust_remote_code=True
 )
 model.cuda()
 inputs = tokenizer("The weather is always wonderful", return_tensors="pt").to(model.device)

config.json

@@ -3,10 +3,6 @@
     "StableLmForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "configuration_stablelm.StableLmConfig",
-    "AutoModelForCausalLM": "modeling_stablelm.StableLmForCausalLM"
-  },
   "bos_token_id": 100257,
   "eos_token_id": 100257,
   "hidden_act": "silu",
@@ -27,7 +23,7 @@
   "rotary_scaling_factor": 1.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.0.dev0",
+  "transformers_version": "4.40.0",
   "use_cache": true,
   "use_norm_bias": false,
   "use_parallel_residual": true,

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 100257,
   "eos_token_id": 100257,
   "pad_token_id": 100257,
-  "transformers_version": "4.39.0.dev0"
+  "transformers_version": "4.40.0"
 }