Teaven commited on
Commit
532b46e
·
verified ·
1 Parent(s): 8ab4d29

Upload folder using huggingface_hub

Browse files
no-warmup-no-decay-4k-no-optim-no-tie-streamingLLM-4-28-qwen2.5dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-5-minlr-2e-5-bs-1024-gpus-8-seqlen-4096/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1920,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4800,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 30,
18
+ "num_hidden_layers": 56,
19
+ "num_key_value_heads": 6,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.51.3",
27
+ "use_cache": true,
28
+ "vocab_size": 99072
29
+ }
no-warmup-no-decay-4k-no-optim-no-tie-streamingLLM-4-28-qwen2.5dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-5-minlr-2e-5-bs-1024-gpus-8-seqlen-4096/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.51.3"
6
+ }
no-warmup-no-decay-4k-no-optim-no-tie-streamingLLM-4-28-qwen2.5dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-5-minlr-2e-5-bs-1024-gpus-8-seqlen-4096/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f46712090ff15799313d49287974e8f06054f23b847ba3722d5a67190cf1ce6a
3
+ size 4849386736
no-warmup-no-decay-4k-no-optim-no-tie-streamingLLM-4-28-qwen2.5dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-5-minlr-2e-5-bs-1024-gpus-8-seqlen-4096/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
no-warmup-no-decay-4k-no-optim-no-tie-streamingLLM-4-28-qwen2.5dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-5-minlr-2e-5-bs-1024-gpus-8-seqlen-4096/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
no-warmup-no-decay-4k-no-optim-no-tie-streamingLLM-4-28-qwen2.5dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-5-minlr-2e-5-bs-1024-gpus-8-seqlen-4096/tokenizer_config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "102": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "103": {
39
+ "content": "<reasoning_step>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "104": {
47
+ "content": "<|start_header_id|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "105": {
55
+ "content": "<|end_header_id|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "106": {
63
+ "content": "<|eot_id|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ }
70
+ },
71
+ "bos_token": "<s>",
72
+ "chat_template": "{% if messages[0]['role'] == 'system' %}\n {% set offset = 1 %}\n{% else %}\n {% set offset = 0 %}\n{% endif %}\n\n{{ bos_token }}\n{% for message in messages %}\n {% if (message['role'] == 'user') != (loop.index0 % 2 == offset) %}\n {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}\n {% endif %}\n\n {{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'] | trim + '<|eot_id|>' }}\n{% endfor %}\n\n{% if add_generation_prompt %}\n {{ '<|start_header_id|>' + 'assistant' + '<|end_header_id|>\n\n' }}\n{% endif %}",
73
+ "clean_up_tokenization_spaces": false,
74
+ "eos_token": "</s>",
75
+ "extra_special_tokens": {},
76
+ "legacy": true,
77
+ "model_max_length": 1000000000000000019884624838656,
78
+ "pad_token": "<pad>",
79
+ "padding_side": "right",
80
+ "sp_model_kwargs": {},
81
+ "spaces_between_special_tokens": false,
82
+ "tokenizer_class": "LlamaTokenizerFast",
83
+ "unk_token": "<unk>",
84
+ "use_default_system_prompt": false
85
+ }