Hugging Face's logo

almanach
/
manta-lm-base

Text2Text Generation
Transformers
PyTorch
English
manta
custom_code
Model card Files Community
1

bs256 version

#1
by nthngdy - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+4
-9
Files changed (2) hide show
  1. config.json +2 -7
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -2,13 +2,8 @@
2
  "architectures": [
3
  "MantaForConditionalGeneration"
4
  ],
5
- "auto_map": {
6
- "AutoConfig": "configuration_manta.MantaConfig",
7
- "AutoModel": "modeling_manta.MantaModel",
8
- "AutoModelForSeq2SeqLM": "modeling_manta.MantaForConditionalGeneration"
9
- },
10
  "byte_embedding_dim": 128,
11
- "d_ff": 2048,
12
  "d_kv": 64,
13
  "d_model": 768,
14
  "dense_act_fn": "gelu_new",
@@ -22,7 +17,7 @@
22
  "is_encoder_decoder": true,
23
  "is_gated_act": true,
24
  "layer_norm_epsilon": 1e-06,
25
- "max_length_encoder_decoder": 512,
26
  "max_length_inputs": 2048,
27
  "model_type": "manta",
28
  "num_decoder_layers": 12,
 
2
  "architectures": [
3
  "MantaForConditionalGeneration"
4
  ],
 
 
 
 
 
5
  "byte_embedding_dim": 128,
6
+ "d_ff": 3072,
7
  "d_kv": 64,
8
  "d_model": 768,
9
  "dense_act_fn": "gelu_new",
 
17
  "is_encoder_decoder": true,
18
  "is_gated_act": true,
19
  "layer_norm_epsilon": 1e-06,
20
+ "max_length_encoder_decoder": 256,
21
  "max_length_inputs": 2048,
22
  "model_type": "manta",
23
  "num_decoder_layers": 12,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5956d10734fc88ffbafc89ad81b371b3be9201e0b25de9818040e4314a9e3a1
3
- size 797912349
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c93fe5198c403ace584c8fc1b56770b7497d35deaf8eb82e2ac71d80fcf15219
3
+ size 1024404765