Merge with linear

config.json

@@ -3,11 +3,13 @@
   "architectures": [
     "GPTBigCodeLMHeadModel"
   ],
+  "attention_softmax_in_fp32": true,
   "attention_type": 2,
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
+  "inference_runner": 0,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt_bigcode",
@@ -16,9 +18,9 @@
   "n_inner": 8192,
   "n_layer": 24,
   "n_positions": 2048,
-  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
+  "runner_max_sequence_length": null,
+  "scale_attention_softmax_in_fp32": true,
   "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
@@ -27,5 +29,6 @@
   "summary_use_proj": true,
   "transformers_version": "4.27.0.dev0",
   "use_cache": true,
+  "validate_runner_input": true,
   "vocab_size": 49280
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90379993a9bff7bbd8749be2a911ead7c410459d616e81b5dc3054bf9045b156
+oid sha256:50d0abae8bfd19082f125e7a40567cba71de296637802eb70157fe55fa66923f
 size 2249864093