Upload model

2025-01-20 15:46:02 +08:00
parent 9b9998f8be
commit b04e8e5a7b
18 changed files with 152310 additions and 1 deletions
--- a/config.json
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/mnt/pfs/nlp/wulixin/exp_dir_etuning_reason/etuning-reason-qwq-sft-qwen25-14b-exp1-2-2024.12.06-12:35:05/models/checkpoint-352",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}