Update config.json

config.json

@@ -1,31 +1,88 @@
 {
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "vinai/PhoGPT-4B-Chat",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 32,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "ffn.down_proj",
-    "attn.out_proj",
-    "ffn.up_proj",
-    "attn.Wqkv"
+  "_name_or_path": "vinai/PhoGPT-4B-Chat",
+  "architectures": [
+    "MPTForCausalLM"
   ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
-}
+  "attn_config": {
+    "alibi": true,
+    "alibi_bias_max": 8,
+    "attn_impl": "torch",
+    "attn_pdrop": 0.0,
+    "attn_type": "multihead_attention",
+    "attn_uses_sequence_id": false,
+    "clip_qkv": null,
+    "prefix_lm": false,
+    "qk_gn": false,
+    "qk_ln": false,
+    "rope": false,
+    "rope_dail_config": {
+      "pos_idx_in_fp32": true,
+      "type": "original",
+      "xpos_scale_base": 512
+    },
+    "rope_hf_config": {
+      "factor": 1.0,
+      "type": "no_scaling"
+    },
+    "rope_impl": "dail",
+    "rope_theta": 10000,
+    "sliding_window_size": -1,
+    "softmax_scale": null
+  },
+  "auto_map": {
+    "AutoConfig": "vinai/PhoGPT-4B-Chat--configuration_mpt.MPTConfig",
+    "AutoModelForCausalLM": "vinai/PhoGPT-4B-Chat--modeling_mpt.MPTForCausalLM"
+  },
+  "d_model": 3072,
+  "emb_pdrop": 0.0,
+  "embedding_fraction": 1.0,
+  "expansion_ratio": 4,
+  "fc_type": "torch",
+  "ffn_config": {
+    "fc_type": "torch",
+    "ffn_type": "mptmlp"
+  },
+  "init_config": {
+    "emb_init_std": null,
+    "emb_init_uniform_lim": null,
+    "fan_mode": "fan_in",
+    "init_div_is_residual": true,
+    "init_gain": 0.0,
+    "init_nonlinearity": "relu",
+    "init_std": null,
+    "name": "kaiming_normal_",
+    "verbose": 0
+  },
+  "init_device": "cpu",
+  "learned_pos_emb": false,
+  "logit_scale": null,
+  "max_seq_len": 8192,
+  "model_type": "mpt",
+  "n_heads": 24,
+  "n_layers": 32,
+  "no_bias": false,
+  "norm_type": "low_precision_layernorm",
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "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": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "resid_pdrop": 0.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "use_pad_tok_in_ffn": true,
+  "verbose": 0,
+  "vocab_size": 20480
+}