Update config.json
Browse files- config.json +32 -29
config.json
CHANGED
|
@@ -1,31 +1,34 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
|
| 5 |
-
"bias": "none",
|
| 6 |
-
"fan_in_fan_out": false,
|
| 7 |
-
"inference_mode": true,
|
| 8 |
-
"init_lora_weights": true,
|
| 9 |
-
"layer_replication": null,
|
| 10 |
-
"layers_pattern": null,
|
| 11 |
-
"layers_to_transform": null,
|
| 12 |
-
"loftq_config": {},
|
| 13 |
-
"lora_alpha": 32,
|
| 14 |
-
"lora_dropout": 0.05,
|
| 15 |
-
"megatron_config": null,
|
| 16 |
-
"megatron_core": "megatron.core",
|
| 17 |
-
"modules_to_save": null,
|
| 18 |
-
"peft_type": "LORA",
|
| 19 |
-
"r": 16,
|
| 20 |
-
"rank_pattern": {},
|
| 21 |
-
"revision": null,
|
| 22 |
-
"target_modules": [
|
| 23 |
-
"fc2",
|
| 24 |
-
"q_proj",
|
| 25 |
-
"v_proj",
|
| 26 |
-
"fc1"
|
| 27 |
],
|
| 28 |
-
"
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "microsoft/phi-1_5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PhiForCausalLM"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
],
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "configuration_phi.PhiConfig",
|
| 8 |
+
"AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
|
| 9 |
+
},
|
| 10 |
+
"attention_dropout": 0.0,
|
| 11 |
+
"bos_token_id": null,
|
| 12 |
+
"embd_pdrop": 0.0,
|
| 13 |
+
"eos_token_id": null,
|
| 14 |
+
"hidden_act": "gelu_new",
|
| 15 |
+
"hidden_size": 2048,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 8192,
|
| 18 |
+
"layer_norm_eps": 1e-05,
|
| 19 |
+
"max_position_embeddings": 2048,
|
| 20 |
+
"model_type": "phi",
|
| 21 |
+
"num_attention_heads": 32,
|
| 22 |
+
"num_hidden_layers": 24,
|
| 23 |
+
"num_key_value_heads": null,
|
| 24 |
+
"partial_rotary_factor": 0.5,
|
| 25 |
+
"qk_layernorm": false,
|
| 26 |
+
"resid_pdrop": 0.0,
|
| 27 |
+
"rope_scaling": null,
|
| 28 |
+
"rope_theta": 10000.0,
|
| 29 |
+
"tie_word_embeddings": false,
|
| 30 |
+
"torch_dtype": "float16",
|
| 31 |
+
"transformers_version": "4.37.0",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 51200
|
| 34 |
+
}
|