Update tiny models for MptForTokenClassification
Browse files- config.json +58 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MptForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.1,
|
| 6 |
+
"attn_config": {
|
| 7 |
+
"alibi": true,
|
| 8 |
+
"alibi_bias_max": 8,
|
| 9 |
+
"attn_impl": "torch",
|
| 10 |
+
"attn_pdrop": 0,
|
| 11 |
+
"attn_type": "multihead_attention",
|
| 12 |
+
"attn_uses_sequence_id": false,
|
| 13 |
+
"clip_qkv": null,
|
| 14 |
+
"model_type": "",
|
| 15 |
+
"prefix_lm": false,
|
| 16 |
+
"qk_ln": false,
|
| 17 |
+
"softmax_scale": null
|
| 18 |
+
},
|
| 19 |
+
"bos_token_id": 0,
|
| 20 |
+
"d_model": 48,
|
| 21 |
+
"dtype": "float32",
|
| 22 |
+
"emb_pdrop": 0.0,
|
| 23 |
+
"embedding_fraction": 1.0,
|
| 24 |
+
"eos_token_id": 0,
|
| 25 |
+
"expansion_ratio": 4,
|
| 26 |
+
"gradient_checkpointing": false,
|
| 27 |
+
"hidden_dropout": 0.1,
|
| 28 |
+
"id2label": {
|
| 29 |
+
"0": "LABEL_0",
|
| 30 |
+
"1": "LABEL_1",
|
| 31 |
+
"2": "LABEL_2"
|
| 32 |
+
},
|
| 33 |
+
"init_device": "cpu",
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"label2id": {
|
| 36 |
+
"LABEL_0": 0,
|
| 37 |
+
"LABEL_1": 1,
|
| 38 |
+
"LABEL_2": 2
|
| 39 |
+
},
|
| 40 |
+
"layer_norm_epsilon": 1e-05,
|
| 41 |
+
"learned_pos_emb": true,
|
| 42 |
+
"logit_scale": null,
|
| 43 |
+
"max_seq_len": 2048,
|
| 44 |
+
"model_type": "mpt",
|
| 45 |
+
"n_heads": 4,
|
| 46 |
+
"n_layers": 2,
|
| 47 |
+
"n_positions": 512,
|
| 48 |
+
"no_bias": true,
|
| 49 |
+
"norm_type": "low_precision_layernorm",
|
| 50 |
+
"pad_token_id": 1,
|
| 51 |
+
"resid_pdrop": 0.0,
|
| 52 |
+
"seq_length": 7,
|
| 53 |
+
"tie_word_embeddings": true,
|
| 54 |
+
"transformers_version": "5.16.0.dev0",
|
| 55 |
+
"type_vocab_size": 16,
|
| 56 |
+
"use_cache": true,
|
| 57 |
+
"vocab_size": 50277
|
| 58 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c7fc099ec10f235128e347d266a8d5b01d282515b8087dcbe03bdde1bc8a582
|
| 3 |
+
size 9877508
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"is_local": true,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
+
"pad_token": "<|padding|>",
|
| 11 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 12 |
+
"trim_offsets": true,
|
| 13 |
+
"unk_token": "<|endoftext|>"
|
| 14 |
+
}
|