Upload model

config.json

@@ -1 +1 @@
-{"config": {"block_size": 1024, "vocab_size": 50257, "n_layer": 4, "n_head": 16, "n_embd": 1024, "dropout": 0.01, "bias": true, "attention": {"attention_type": "default_attention", "scaling_factor": 3}, "activation": "gelu", "epsilon": 1e-05}, "model_type": "llm_gym_gpt2"}
+{"config": {"sample_key": "input_ids", "prediction_key": "logits", "block_size": 1024, "vocab_size": 50304, "n_layer": 4, "n_head": 16, "n_embd": 1024, "ffn_hidden": 4096, "dropout": 0.01, "bias": true, "attention": {"attention_type": "default_attention", "scaling_factor": 3}, "activation": "gelu", "epsilon": 1e-05, "weight_init": {"mean": 0.0, "std": 0.02}}, "model_type": "llm_gym_gpt2"}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff867772261987632087e2b5e2809bffe614113357e59ab255cf157b9a867e8d
-size 428390038
+oid sha256:d316a9243e369c6c08280237ba2127cfc39d19294c2368cddd22d755d8fb642d
+size 428582550