Upload PhiForCausalLM
Browse files- config.json +4 -4
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -9,9 +9,9 @@
|
|
| 9 |
"embd_pdrop": 0.0,
|
| 10 |
"eos_token_id": 50256,
|
| 11 |
"hidden_act": "gelu_new",
|
| 12 |
-
"hidden_size":
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size":
|
| 15 |
"layer_norm_eps": 1e-05,
|
| 16 |
"max_position_embeddings": 2048,
|
| 17 |
"model_type": "phi",
|
|
@@ -19,13 +19,13 @@
|
|
| 19 |
"num_beams": null,
|
| 20 |
"num_hidden_layers": 16,
|
| 21 |
"num_key_value_heads": 32,
|
| 22 |
-
"partial_rotary_factor": 0.
|
| 23 |
"qk_layernorm": false,
|
| 24 |
"resid_pdrop": 0.1,
|
| 25 |
"rope_scaling": null,
|
| 26 |
"rope_theta": 10000.0,
|
| 27 |
"tie_word_embeddings": false,
|
| 28 |
-
"torch_dtype": "
|
| 29 |
"transformers_version": "4.45.2",
|
| 30 |
"use_cache": true,
|
| 31 |
"vocab_size": 51200
|
|
|
|
| 9 |
"embd_pdrop": 0.0,
|
| 10 |
"eos_token_id": 50256,
|
| 11 |
"hidden_act": "gelu_new",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 8192,
|
| 15 |
"layer_norm_eps": 1e-05,
|
| 16 |
"max_position_embeddings": 2048,
|
| 17 |
"model_type": "phi",
|
|
|
|
| 19 |
"num_beams": null,
|
| 20 |
"num_hidden_layers": 16,
|
| 21 |
"num_key_value_heads": 32,
|
| 22 |
+
"partial_rotary_factor": 0.5,
|
| 23 |
"qk_layernorm": false,
|
| 24 |
"resid_pdrop": 0.1,
|
| 25 |
"rope_scaling": null,
|
| 26 |
"rope_theta": 10000.0,
|
| 27 |
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
"transformers_version": "4.45.2",
|
| 30 |
"use_cache": true,
|
| 31 |
"vocab_size": 51200
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27d1084bd29d4479f4ef4642f033dc0ab9645dcc1f54548e3958b6333a649e70
|
| 3 |
+
size 2030899760
|