Add Qwen2.5-tiny model with single hidden layer

config.json

@@ -9,19 +9,25 @@
   "hidden_size": 64,
   "initializer_range": 0.02,
   "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
   "max_position_embeddings": 327,
   "max_window_layers": 24,
   "model_type": "qwen2",
   "num_attention_heads": 6,
-  "num_hidden_layers": 1,
+  "num_hidden_layers": 4,
   "num_key_value_heads": 2,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
-  "sliding_window": 327,
+  "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.52.4",
+  "transformers_version": "4.55.0",
   "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 151643,
   "eos_token_id": 151643,
-  "transformers_version": "4.52.4"
+  "transformers_version": "4.55.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37039fe993775b47e3ab5ce55c09a9408a638989a0497db3af5b11755d3c21ed
-size 21338160
+oid sha256:78c041d8be4c4764f840bab7d8d5ff2a09668f7194599508494bcb0ffd59fd6a
+size 27008160