Upload GexQwenForCausalLM

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "GexQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_gex.GexConfig",
+    "AutoModelForCausalLM": "modeling_gex.GexQwenForCausalLM"
+  },
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 8,
+  "model_type": "gex",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration_gex.py

@@ -0,0 +1,4 @@
+from transformers import Qwen2Config
+
+class GexConfig(Qwen2Config):
+    model_type = "gex"

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "transformers_version": "4.50.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896799e932d917484780c2776cfb8363d51e95b2af58df9c631b3b41bcf41dde
+size 714447688