Hugging Face's logo

filipesantoscv11
/
ec00854d-2805-4104-9794-4e5501f76449

PEFT
Safetensors
gpt_neo
axolotl
Generated from Trainer
Model card Files Community
filipesantoscv11 commited on
Commit
9990c3e
·
verified ·
1 Parent(s): 385d176

Training in progress, step 10

Browse files
Files changed (9) hide show
  1. adapter_config.json +33 -0
  2. adapter_model.safetensors +3 -0
  3. config.json +75 -0
  4. merges.txt +0 -0
  5. special_tokens_map.json +30 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +23 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "EleutherAI/gpt-neo-1.3B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "v_proj",
25
+ "out_proj",
26
+ "q_proj",
27
+ "c_fc",
28
+ "c_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daac12040c5c9908254d9ca5fe9bf64de0655d73b5ce945a8014b08e10e93c55
3
+ size 56662456
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "EleutherAI/gpt-neo-1.3B",
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPTNeoForCausalLM"
7
+ ],
8
+ "attention_dropout": 0,
9
+ "attention_layers": [
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local",
16
+ "global",
17
+ "local",
18
+ "global",
19
+ "local",
20
+ "global",
21
+ "local",
22
+ "global",
23
+ "local",
24
+ "global",
25
+ "local",
26
+ "global",
27
+ "local",
28
+ "global",
29
+ "local",
30
+ "global",
31
+ "local",
32
+ "global",
33
+ "local"
34
+ ],
35
+ "attention_types": [
36
+ [
37
+ [
38
+ "global",
39
+ "local"
40
+ ],
41
+ 12
42
+ ]
43
+ ],
44
+ "bos_token_id": 50256,
45
+ "classifier_dropout": 0.1,
46
+ "embed_dropout": 0,
47
+ "eos_token_id": 50256,
48
+ "gradient_checkpointing": false,
49
+ "hidden_size": 2048,
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": null,
52
+ "layer_norm_epsilon": 1e-05,
53
+ "max_position_embeddings": 2048,
54
+ "model_type": "gpt_neo",
55
+ "num_heads": 16,
56
+ "num_layers": 24,
57
+ "resid_dropout": 0,
58
+ "summary_activation": null,
59
+ "summary_first_dropout": 0.1,
60
+ "summary_proj_to_labels": true,
61
+ "summary_type": "cls_index",
62
+ "summary_use_proj": true,
63
+ "task_specific_params": {
64
+ "text-generation": {
65
+ "do_sample": true,
66
+ "max_length": 50,
67
+ "temperature": 0.9
68
+ }
69
+ },
70
+ "tokenizer_class": "GPT2Tokenizer",
71
+ "transformers_version": "4.46.0",
72
+ "use_cache": false,
73
+ "vocab_size": 50257,
74
+ "window_size": 256
75
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
16
+ "clean_up_tokenization_spaces": false,
17
+ "eos_token": "<|endoftext|>",
18
+ "errors": "replace",
19
+ "model_max_length": 2048,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:429d0482757c1d9810adb9d2045563be254cf9bb6f589f4f9cd77ebf7c4d4447
3
+ size 6776
vocab.json ADDED
The diff for this file is too large to render. See raw diff