AksharaBalan commited on
Commit
b91a159
·
verified ·
1 Parent(s): d926c03

Upload model

Browse files
Files changed (3) hide show
  1. README.md +3 -0
  2. config.json +33 -1
  3. model.safetensors +3 -0
README.md CHANGED
@@ -1,3 +1,6 @@
 
 
 
1
  # MiniGPT for Malayalam
2
 
3
  This is a small-scale GPT model trained on Malayalam text using SentencePiece and PyTorch.
 
1
+ ---
2
+ {}
3
+ ---
4
  # MiniGPT for Malayalam
5
 
6
  This is a small-scale GPT model trained on Malayalam text using SentencePiece and PyTorch.
config.json CHANGED
@@ -1 +1,33 @@
1
- {"model_type": "gpt2","vocab_size": 5000, "n_embd": 256, "n_layer": 1, "n_head": 4, "context_length": 256}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "AksharaBalan/malayalam-minigpt",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2Model"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "context_length": 256,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_embd": 256,
16
+ "n_head": 4,
17
+ "n_inner": null,
18
+ "n_layer": 1,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.47.0",
31
+ "use_cache": true,
32
+ "vocab_size": 5000
33
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c432f41fbdc3b1376214263390db574a4eb05ba0125cb50bc504c8368149ab7
3
+ size 9331032