Upload text_model_cfg.json
Browse files- text_model_cfg.json +31 -0
text_model_cfg.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/phi-1_5",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"PhiForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "configuration_phi.PhiConfig",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_phi.PhiForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"embd_pdrop": 0.0,
|
| 13 |
+
"flash_attn": false,
|
| 14 |
+
"flash_rotary": false,
|
| 15 |
+
"fused_dense": false,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"layer_norm_epsilon": 1e-05,
|
| 18 |
+
"model_type": "phi-msft",
|
| 19 |
+
"n_embd": 2048,
|
| 20 |
+
"n_head": 32,
|
| 21 |
+
"n_head_kv": null,
|
| 22 |
+
"n_inner": null,
|
| 23 |
+
"n_layer": 24,
|
| 24 |
+
"n_positions": 2048,
|
| 25 |
+
"resid_pdrop": 0.0,
|
| 26 |
+
"rotary_dim": 32,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float16",
|
| 29 |
+
"transformers_version": "4.34.1",
|
| 30 |
+
"vocab_size": 51200
|
| 31 |
+
}
|