Upload Qwen2ForCausalLM

config.json

@@ -1,29 +1,29 @@
 {
-  "_name_or_path": "/home/michele/merge/merge_model/qwen3b",
+  "_name_or_path": "/home/michele/merge/merge_model/qwen3_dpo_llm",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "eos_token_id": 151645,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 32768,
-  "max_window_layers": 70,
+  "max_window_layers": 36,
   "model_type": "qwen2",
   "num_attention_heads": 16,
   "num_hidden_layers": 36,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.2",
+  "transformers_version": "4.44.0",
   "use_cache": false,
+  "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -1,14 +1,6 @@
 {
   "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "repetition_penalty": 1.05,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
-  "transformers_version": "4.45.2"
+  "eos_token_id": 151645,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.44.0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d15d0d0792395677f3e8d0eac7334cc27df07770a9ff00e8a8dd06f50e7740d
+oid sha256:e96cf510f2c6b0cd75f80c8bae9e18a3e865fa44c1423a212a3b6091c2b318d9
 size 4957560304

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7972eb7e5de2483850b6ad80922a120f277d66a9644865aa95549718900cf461
+oid sha256:7fc5d2e8676388a0661c1c218616dea282fd443d2bb2f74d741e0fa9bb5e9f3a
 size 1214366696