hellonet22 commited on
Commit
8b8d1d6
·
verified ·
1 Parent(s): 1e0c96b

Training in progress, step 5000

Browse files
Files changed (3) hide show
  1. config.json +22 -32
  2. model.safetensors +2 -2
  3. training_args.bin +1 -1
config.json CHANGED
@@ -1,39 +1,29 @@
1
  {
2
- "_name_or_path": "gpt2",
3
- "activation_function": "gelu_new",
4
  "architectures": [
5
- "GPT2LMHeadModel"
6
  ],
7
- "attn_pdrop": 0.1,
8
- "bos_token_id": 0,
9
- "embd_pdrop": 0.1,
10
- "eos_token_id": 0,
 
 
 
 
 
11
  "initializer_range": 0.02,
12
- "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
- "n_ctx": 128,
15
- "n_embd": 768,
16
- "n_head": 12,
17
- "n_inner": null,
18
- "n_layer": 12,
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
- "task_specific_params": {
30
- "text-generation": {
31
- "do_sample": true,
32
- "max_length": 50
33
- }
34
- },
35
  "torch_dtype": "float32",
36
- "transformers_version": "4.44.0",
37
  "use_cache": true,
38
- "vocab_size": 50000
 
 
39
  }
 
1
  {
 
 
2
  "architectures": [
3
+ "HGRNBitForCausalLM"
4
  ],
5
+ "attn_mode": "fused_recurrent",
6
+ "bos_token_id": 1,
7
+ "conv_size": 4,
8
+ "eos_token_id": 2,
9
+ "expand_ratio": 1,
10
+ "fuse_cross_entropy": true,
11
+ "hidden_act": "swish",
12
+ "hidden_ratio": 4,
13
+ "hidden_size": 1024,
14
  "initializer_range": 0.02,
15
+ "intermediate_size": null,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "hgrn_bit",
18
+ "num_heads": 1,
19
+ "num_hidden_layers": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "share_conv_kernel": true,
22
+ "tie_word_embeddings": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  "torch_dtype": "float32",
24
+ "transformers_version": "4.45.0.dev0",
25
  "use_cache": true,
26
+ "use_lower_bound": true,
27
+ "use_short_conv": false,
28
+ "vocab_size": 50257
29
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13e9591b03b92eca07cfc9fdf5e002087233305716ed21e81e658ecb14904754
3
- size 496984704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124fb8817a210b853f2786c3997d5a679d0d23eb340426a1cd5c518cffb7a282
3
+ size 463144000
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:921b916935fe576ea7c3464092a599cc93ad43256ea30b76eec304571230cea6
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eee3af6352a91c1e4b587ce720c6ad3b8e3606f20adeeddec9b5e805ee2461bf
3
  size 5112