uploaded model

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "xglm-4.5B",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "XGLMForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "attention_heads": 16,
+  "bos_token_id": 0,
+  "d_model": 2048,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 16384,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "xglm",
+  "num_layers": 48,
+  "pad_token_id": 1,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "scale_embedding": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 256008
+}