Create config.json

config.json

@@ -0,0 +1,67 @@
+{
+  "architectures": [
+    "KirimForCausalLM"
+  ],
+  "model_type": "kirim",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.0",
+  
+  "_name_or_path": "Kirim-ai/Kirim-V1-base",
+  "vocab_size": 102400,
+  "hidden_size": 4096,
+  "intermediate_size": 11008,
+  "num_hidden_layers": 32,
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "hidden_act": "silu",
+  "max_position_embeddings": 32768,
+  "initializer_range": 0.02,
+  "rms_norm_eps": 1e-06,
+  "use_cache": true,
+  "pad_token_id": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "tie_word_embeddings": false,
+  "rope_theta": 10000.0,
+  "rope_scaling": {
+    "type": "yarn",
+    "factor": 2.0,
+    "original_max_position_embeddings": 16384
+  },
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "mlp_bias": false,
+  
+  "use_flash_attention_2": true,
+  "use_sliding_window": false,
+  "sliding_window": null,
+  
+  "quantization_config": {
+    "quant_method": "gptq",
+    "bits": 4,
+    "group_size": 128,
+    "damp_percent": 0.01,
+    "desc_act": false,
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true,
+    "model_name_or_path": null,
+    "model_file_base_name": "model"
+  },
+  
+  "auto_map": {
+    "AutoConfig": "configuration_kirim.KirimConfig",
+    "AutoModelForCausalLM": "modeling_kirim.KirimForCausalLM"
+  },
+  
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 2048,
+      "temperature": 0.7,
+      "top_p": 0.9,
+      "top_k": 50,
+      "repetition_penalty": 1.1
+    }
+  }
+}