Upload config.json with huggingface_hub

config.json

@@ -1,29 +1,29 @@
-{
-  "_name_or_path": "./saves/gemma-7b/sft-full-V3-4/checkpoint-4877",
-  "architectures": [
-    "GemmaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 2,
-  "eos_token_id": 1,
-  "head_dim": 256,
-  "hidden_act": "gelu",
-  "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 3072,
-  "initializer_range": 0.02,
-  "intermediate_size": 24576,
-  "max_position_embeddings": 8192,
-  "model_type": "gemma",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 16,
-  "pad_token_id": 0,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.43.1",
-  "use_cache": false,
-  "vocab_size": 256000
-}
+{
+  "_name_or_path": "./saves/gemma/instruct-v4-instruct/checkpoint-6214",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": false,
+  "vocab_size": 256000
+}