Upload 5 files
Browse filesUpload SEA LION 3B base model files
- config.json +56 -0
- generation_config.json +5 -0
- pytorch_model-001.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +13 -0
config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MPTForCausalLM"
|
4 |
+
],
|
5 |
+
"attn_config": {
|
6 |
+
"alibi": false,
|
7 |
+
"alibi_bias_max": 8,
|
8 |
+
"attn_impl": "torch",
|
9 |
+
"attn_pdrop": 0.0,
|
10 |
+
"attn_type": "multihead_attention",
|
11 |
+
"attn_uses_sequence_id": false,
|
12 |
+
"clip_qkv": null,
|
13 |
+
"prefix_lm": false,
|
14 |
+
"qk_ln": false,
|
15 |
+
"softmax_scale": null
|
16 |
+
},
|
17 |
+
"auto_map": {
|
18 |
+
"AutoConfig": "configuration_mpt.MPTConfig",
|
19 |
+
"AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
|
20 |
+
},
|
21 |
+
"d_model": 2560,
|
22 |
+
"emb_pdrop": 0.0,
|
23 |
+
"embedding_fraction": 1.0,
|
24 |
+
"expansion_ratio": 4,
|
25 |
+
"fc_type": "torch",
|
26 |
+
"ffn_config": {
|
27 |
+
"fc_type": "torch",
|
28 |
+
"ffn_type": "mptmlp"
|
29 |
+
},
|
30 |
+
"init_config": {
|
31 |
+
"emb_init_std": null,
|
32 |
+
"emb_init_uniform_lim": null,
|
33 |
+
"fan_mode": "fan_in",
|
34 |
+
"init_div_is_residual": true,
|
35 |
+
"init_gain": 0.0,
|
36 |
+
"init_nonlinearity": "relu",
|
37 |
+
"init_std": null,
|
38 |
+
"name": "kaiming_normal_",
|
39 |
+
"verbose": 0
|
40 |
+
},
|
41 |
+
"init_device": "cpu",
|
42 |
+
"learned_pos_emb": true,
|
43 |
+
"logit_scale": null,
|
44 |
+
"max_seq_len": 2048,
|
45 |
+
"model_type": "mpt",
|
46 |
+
"n_heads": 20,
|
47 |
+
"n_layers": 32,
|
48 |
+
"no_bias": false,
|
49 |
+
"norm_type": "low_precision_layernorm",
|
50 |
+
"resid_pdrop": 0.0,
|
51 |
+
"torch_dtype": "bfloat16",
|
52 |
+
"transformers_version": "4.31.0",
|
53 |
+
"use_cache": false,
|
54 |
+
"verbose": 0,
|
55 |
+
"vocab_size": 256000
|
56 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.31.0",
|
4 |
+
"use_cache": false
|
5 |
+
}
|
pytorch_model-001.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aeea62ff5b8b0ca08e67926eb413bec3594bd330be16d2fbc9624bbb47650f02
|
3 |
+
size 6356636361
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": null,
|
5 |
+
"clean_up_tokenization_spaces": false,
|
6 |
+
"eos_token": null,
|
7 |
+
"legacy": null,
|
8 |
+
"model_max_length": 1000000000000000019884624838656,
|
9 |
+
"pad_token": null,
|
10 |
+
"sp_model_kwargs": {},
|
11 |
+
"tokenizer_class": "SEABPETokenizer",
|
12 |
+
"unk_token": null
|
13 |
+
}
|