Upload trained model ysnrfd-base

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "YsnrfdForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "early_stopping_patience": 3,
+  "eos_token_id": 50256,
+  "gradient_accumulation_steps": 4,
+  "gradient_checkpointing": false,
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "model_type": "ysnrfd",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 50256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_flash_attn": false,
+  "use_gradient_accumulation": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "pad_token_id": 50256,
+  "transformers_version": "4.57.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97a88ebbcd04cd838451870d153da0267e2908fa2dddfce3c846eaf81025816a
+size 607488539

trainer_state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cacb200b4dbbcbd4e17da87903fc3be4b338e7fcd22cea034189de6056c71bae
+size 1214997259