Hugging Face's logo

deepnet
/
PreTrainingSubnetModel

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Model card Files
xet
Community
deepnet commited on
Commit
424e1c0
·
verified ·
1 Parent(s): adb5ebe

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +21 -32
  2. generation_config.json +2 -2
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,39 +1,28 @@
1
  {
2
- "_name_or_path": "/Pretraining-Testing/pretraining/local-models/training/2024-01-23_14-59-41",
3
- "activation_function": "gelu_new",
4
  "architectures": [
5
- "GPT2LMHeadModel"
6
  ],
7
- "attn_pdrop": 0.0,
8
- "bos_token_id": 50256,
9
- "embd_pdrop": 0.0,
10
- "eos_token_id": 50256,
11
- "initializer_range": 0.02,
12
- "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
- "n_ctx": 1024,
15
- "n_embd": 768,
16
- "n_head": 12,
17
- "n_inner": null,
18
- "n_layer": 20,
19
- "n_positions": 1024,
20
- "reorder_and_upcast_attn": false,
21
- "resid_pdrop": 0.0,
22
- "scale_attn_by_inverse_layer_idx": false,
23
- "scale_attn_weights": true,
24
- "summary_activation": null,
25
- "summary_first_dropout": 0.0,
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": "4.34.1",
37
  "use_cache": true,
38
- "vocab_size": 50257
39
  }
 
1
  {
2
+ "_name_or_path": "/finetuning-subnet/nous-four",
 
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4,
12
+ "initializer_range": 0.0,
13
+ "intermediate_size": 4,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 1,
17
+ "num_hidden_layers": 4,
18
+ "num_key_value_heads": 1,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
 
 
 
 
 
 
 
 
 
 
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.34.1",
26
  "use_cache": true,
27
+ "vocab_size": 32000
28
  }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
  "transformers_version": "4.34.1"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
  "transformers_version": "4.34.1"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:096565917ce3134ba42f911e672757a802dcdb73c4181a6f591c55785034e6be
3
- size 724595976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:403c69aa70694430c1bd0109adbf13f17510d2e0afc313b4e0f8f2f3311e6883
3
+ size 1029944