Upload config.json with huggingface_hub

config.json

@@ -1,30 +1,30 @@
 {
-"_name_or_path": "/data/k2-ckpts/hf/k2-chat",
-"architectures": [
-"LlamaForCausalLM"
-],
-"attention_bias": false,
-"attention_dropout": 0,
-"bos_token_id": 1,
-"eos_token_id": 2,
-"hidden_act": "silu",
-"hidden_size": 8192,
-"initializer_range": 0.02,
-"intermediate_size": 22016,
-"max_position_embeddings": 2048,
-"max_sequence_length": 2048,
-"model_type": "llama",
-"num_attention_heads": 64,
-"num_hidden_layers": 80,
-"num_key_value_heads": 64,
-"pad_token_id": 0,
-"pretraining_tp": 1,
-"rms_norm_eps": 0.00001,
-"rope_scaling": null,
-"rope_theta": 500000,
-"tie_word_embeddings": false,
-"torch_dtype": "float16",
-"transformers_version": "4.39.3",
-"use_cache": true,
-"vocab_size": 32032
+  "_name_or_path": "huggyllama/llama-65b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_position_embeddings": 8192,
+  "max_sequence_length": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 64,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 32032
 }