Hugging Face's logo

kevin1010607
/
llama2-7b-mod-sft-full

Text Generation
Transformers
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
kevin1010607 commited on
Commit
9cff424
·
verified ·
1 Parent(s): d5dfae8

Training in progress, epoch 0

Browse files
Files changed (10) hide show
  1. config.json +29 -0
  2. runs/Jun20_04-11-26_v1vh8qctr1718708466685-nzm8x/events.out.tfevents.1718827927.v1vh8qctr1718708466685-nzm8x.19220.0 +3 -0
  3. runs/Jun20_04-15-35_v1vh8qctr1718708466685-nzm8x/events.out.tfevents.1718828175.v1vh8qctr1718708466685-nzm8x.25179.0 +3 -0
  4. runs/Jun20_04-18-24_v1vh8qctr1718708466685-nzm8x/events.out.tfevents.1718828342.v1vh8qctr1718708466685-nzm8x.28492.0 +3 -0
  5. runs/Jun20_04-22-13_v1vh8qctr1718708466685-nzm8x/events.out.tfevents.1718828573.v1vh8qctr1718708466685-nzm8x.32192.0 +3 -0
  6. special_tokens_map.json +24 -0
  7. tokenizer.json +0 -0
  8. tokenizer.model +3 -0
  9. tokenizer_config.json +42 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kevin1010607/llama2-7b-mod",
3
+ "architectures": [
4
+ "LlamaMoDForCausalLM"
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": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 32,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.41.2",
27
+ "use_cache": false,
28
+ "vocab_size": 32000
29
+ }
runs/Jun20_04-11-26_v1vh8qctr1718708466685-nzm8x/events.out.tfevents.1718827927.v1vh8qctr1718708466685-nzm8x.19220.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3fea9b4b42abe2b7b994acd23b098e1c8f1e3214e0ed9d9a094782036cea489
3
+ size 5196
runs/Jun20_04-15-35_v1vh8qctr1718708466685-nzm8x/events.out.tfevents.1718828175.v1vh8qctr1718708466685-nzm8x.25179.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:702d8d28a2919f84d859dc410b4225309b03a7cdecc245e0a43f219f828a5f40
3
+ size 4989
runs/Jun20_04-18-24_v1vh8qctr1718708466685-nzm8x/events.out.tfevents.1718828342.v1vh8qctr1718708466685-nzm8x.28492.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3abf43e69a1953a19ff260b55121ac0dbdd35a45d6dd775f264539aac23f9fc
3
+ size 4989
runs/Jun20_04-22-13_v1vh8qctr1718708466685-nzm8x/events.out.tfevents.1718828573.v1vh8qctr1718708466685-nzm8x.32192.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e76a26f6e9d11af429bcac19249d46b861f657d867d83ad3d22d9dda473823
3
+ size 58700
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 2048,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96fa7a7258563bdbe96959d34bcaff4db4ce0c463a3b8a6ed35c17a5fe31cb4c
3
+ size 6584