Upload Qwen2ForCausalLM

README.md

@@ -1,6 +1,8 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- trl
+- sft
 ---
 
 # Model Card for Model ID

config.json

@@ -1,20 +1,24 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-1.5B-instruct",
+  "_name_or_path": "test1",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "eos_token_id": 151645,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 1536,
   "initializer_range": 0.02,
   "intermediate_size": 8960,
-  "max_position_embeddings": 32768,
-  "max_window_layers": 21,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
   "model_type": "qwen2",
+  "new_layer_indices": [
+    29,
+    14
+  ],
   "num_attention_heads": 12,
-  "num_hidden_layers": 28,
+  "num_hidden_layers": 30,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
@@ -24,6 +28,7 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.2",
   "use_cache": true,
+  "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -1,14 +1,6 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "repetition_penalty": 1.1,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
+  "eos_token_id": 151643,
   "transformers_version": "4.46.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd924a11b4c220f385b51ffa522daea7c9f3d850e31b162bb5661df483c6d3ee
-size 3087467144
+oid sha256:bc4dba4f492953e718c3116423c264511e84060d4dc760f34cacf19d36818f35
+size 3274661200