gguichard commited on
Commit
a82b5d0
1 Parent(s): f97ab7a

Upload PhiForTokenClassification

Browse files
Files changed (2) hide show
  1. config.json +21 -22
  2. model.safetensors +2 -2
config.json CHANGED
@@ -1,15 +1,13 @@
1
  {
2
- "_name_or_path": "bigscience-data/sgpt-bloom-1b7-nli",
3
- "apply_residual_connection_post_layernorm": false,
4
  "architectures": [
5
- "BloomForTokenClassification"
6
  ],
7
  "attention_dropout": 0.0,
8
- "attention_softmax_in_fp32": true,
9
- "bias_dropout_fusion": true,
10
- "bos_token_id": 50256,
11
- "eos_token_id": 50256,
12
- "hidden_dropout": 0.0,
13
  "hidden_size": 2048,
14
  "id2label": {
15
  "0": "LABEL_0",
@@ -35626,6 +35624,7 @@
35626
  "35611": "LABEL_35611"
35627
  },
35628
  "initializer_range": 0.02,
 
35629
  "label2id": {
35630
  "LABEL_0": 0,
35631
  "LABEL_1": 1,
@@ -71240,14 +71239,14 @@
71240
  "LABEL_9998": 9998,
71241
  "LABEL_9999": 9999
71242
  },
71243
- "layer_norm_epsilon": 1e-05,
71244
- "masked_softmax_fusion": true,
71245
- "model_type": "bloom",
71246
- "n_head": 16,
71247
- "n_inner": null,
71248
- "n_layer": 24,
71249
- "offset_alibi": 100,
71250
- "pretraining_tp": 1,
71251
  "quantization_config": {
71252
  "_load_in_4bit": true,
71253
  "_load_in_8bit": false,
@@ -71263,12 +71262,12 @@
71263
  "load_in_8bit": false,
71264
  "quant_method": "bitsandbytes"
71265
  },
71266
- "seq_length": 4096,
71267
- "skip_bias_add": true,
71268
- "skip_bias_add_qkv": false,
71269
- "slow_but_exact": false,
71270
  "torch_dtype": "bfloat16",
71271
  "transformers_version": "4.41.2",
71272
- "use_cache": false,
71273
- "vocab_size": 250880
71274
  }
 
1
  {
2
+ "_name_or_path": "microsoft/phi-1_5",
 
3
  "architectures": [
4
+ "PhiForTokenClassification"
5
  ],
6
  "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "embd_pdrop": 0.0,
9
+ "eos_token_id": null,
10
+ "hidden_act": "gelu_new",
 
11
  "hidden_size": 2048,
12
  "id2label": {
13
  "0": "LABEL_0",
 
35624
  "35611": "LABEL_35611"
35625
  },
35626
  "initializer_range": 0.02,
35627
+ "intermediate_size": 8192,
35628
  "label2id": {
35629
  "LABEL_0": 0,
35630
  "LABEL_1": 1,
 
71239
  "LABEL_9998": 9998,
71240
  "LABEL_9999": 9999
71241
  },
71242
+ "layer_norm_eps": 1e-05,
71243
+ "max_position_embeddings": 2048,
71244
+ "model_type": "phi",
71245
+ "num_attention_heads": 32,
71246
+ "num_hidden_layers": 24,
71247
+ "num_key_value_heads": 32,
71248
+ "partial_rotary_factor": 0.5,
71249
+ "qk_layernorm": false,
71250
  "quantization_config": {
71251
  "_load_in_4bit": true,
71252
  "_load_in_8bit": false,
 
71262
  "load_in_8bit": false,
71263
  "quant_method": "bitsandbytes"
71264
  },
71265
+ "resid_pdrop": 0.0,
71266
+ "rope_scaling": null,
71267
+ "rope_theta": 10000.0,
71268
+ "tie_word_embeddings": false,
71269
  "torch_dtype": "bfloat16",
71270
  "transformers_version": "4.41.2",
71271
+ "use_cache": true,
71272
+ "vocab_size": 51200
71273
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35c23dafc7eb0c86a0401610c4b9ba2248c889dd3e154dd517b27ca5fcfbe1a7
3
- size 1854399656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aeb2e58ee3d5449e1a78af3ff0ed3665599a7020758acae0cca556028a72a0a
3
+ size 1036329376