Upload PhiForCausalLM

config.json

@@ -1,46 +1,34 @@
 {
   "_name_or_path": "microsoft/phi-2",
-  "activation_function": "gelu_new",
   "architectures": [
     "PhiForCausalLM"
   ],
-  "attn_pdrop": 0.0,
+  "attention_dropout": 0.0,
   "auto_map": {
     "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
     "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
   },
+  "bos_token_id": 50256,
   "embd_pdrop": 0.0,
-  "flash_attn": true,
-  "flash_rotary": true,
-  "fused_dense": true,
-  "img_processor": null,
+  "eos_token_id": 50256,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "phi-msft",
-  "n_embd": 2560,
-  "n_head": 32,
-  "n_head_kv": null,
-  "n_inner": null,
-  "n_layer": 32,
-  "n_positions": 2048,
-  "pretraining_tp": 1,
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
-    "bnb_4bit_quant_type": "nf4",
-    "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": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
   "resid_pdrop": 0.1,
-  "rotary_dim": 32,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.37.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 51200
 }

generation_config.json

@@ -1,4 +1,6 @@
 {
   "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
   "transformers_version": "4.37.2"
 }