sumo43 commited on
Commit
4dc01c2
1 Parent(s): 3b1b737

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ rank0.engine filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.9.0.dev2024031200",
3
+ "pretrained_config": {
4
+ "architecture": "LlamaForCausalLM",
5
+ "dtype": "float16",
6
+ "logits_dtype": "float32",
7
+ "vocab_size": 32000,
8
+ "max_position_embeddings": 4096,
9
+ "hidden_size": 4096,
10
+ "num_hidden_layers": 32,
11
+ "num_attention_heads": 32,
12
+ "num_key_value_heads": 32,
13
+ "head_size": 128,
14
+ "hidden_act": "silu",
15
+ "intermediate_size": 11008,
16
+ "norm_epsilon": 1e-05,
17
+ "position_embedding_type": "rope_gpt_neox",
18
+ "use_prompt_tuning": false,
19
+ "use_parallel_embedding": false,
20
+ "embedding_sharding_dim": 0,
21
+ "share_embedding_table": false,
22
+ "mapping": {
23
+ "world_size": 1,
24
+ "tp_size": 1,
25
+ "pp_size": 1
26
+ },
27
+ "quantization": {
28
+ "quant_algo": null,
29
+ "kv_cache_quant_algo": null,
30
+ "group_size": 128,
31
+ "has_zero_point": false,
32
+ "pre_quant_scale": false,
33
+ "exclude_modules": [
34
+ "lm_head"
35
+ ]
36
+ },
37
+ "kv_dtype": "float16",
38
+ "max_lora_rank": 64,
39
+ "rotary_scaling": null,
40
+ "moe_normalization_mode": null,
41
+ "rotary_base": 10000.0,
42
+ "moe_num_experts": 0,
43
+ "moe_top_k": 0,
44
+ "moe_tp_mode": 2,
45
+ "attn_bias": false,
46
+ "disable_weight_only_quant_plugin": false,
47
+ "mlp_bias": false
48
+ },
49
+ "build_config": {
50
+ "max_input_len": 1024,
51
+ "max_output_len": 1024,
52
+ "max_batch_size": 1,
53
+ "max_beam_width": 1,
54
+ "max_num_tokens": 1024,
55
+ "max_prompt_embedding_table_size": 0,
56
+ "gather_context_logits": false,
57
+ "gather_generation_logits": false,
58
+ "strongly_typed": false,
59
+ "builder_opt": null,
60
+ "profiling_verbosity": "layer_names_only",
61
+ "enable_debug_output": false,
62
+ "max_draft_len": 0,
63
+ "use_refit": false,
64
+ "auto_parallel_config": {
65
+ "world_size": 1,
66
+ "gpus_per_node": 8,
67
+ "cluster_key": "L40",
68
+ "cluster_info": null,
69
+ "sharding_cost_model": "alpha_beta",
70
+ "comm_cost_model": "alpha_beta",
71
+ "enable_pipeline_parallelism": false,
72
+ "enable_shard_unbalanced_shape": false,
73
+ "enable_shard_dynamic_shape": false,
74
+ "enable_reduce_scatter": true,
75
+ "builder_flags": null,
76
+ "debug_mode": false,
77
+ "infer_shape": true,
78
+ "validation_mode": false,
79
+ "same_buffer_io": {
80
+ "past_key_value_(\\d+)": "present_key_value_\\1"
81
+ },
82
+ "same_spec_io": {},
83
+ "sharded_io_allowlist": [
84
+ "past_key_value_\\d+",
85
+ "present_key_value_\\d*"
86
+ ],
87
+ "fast_reduce": true,
88
+ "fill_weights": false,
89
+ "parallel_config_cache": null,
90
+ "profile_cache": null,
91
+ "dump_path": null,
92
+ "debug_outputs": []
93
+ },
94
+ "plugin_config": {
95
+ "bert_attention_plugin": "float16",
96
+ "gpt_attention_plugin": "float16",
97
+ "gemm_plugin": "float16",
98
+ "smooth_quant_gemm_plugin": null,
99
+ "identity_plugin": null,
100
+ "layernorm_quantization_plugin": null,
101
+ "rmsnorm_quantization_plugin": null,
102
+ "nccl_plugin": null,
103
+ "lookup_plugin": null,
104
+ "lora_plugin": null,
105
+ "weight_only_groupwise_quant_matmul_plugin": null,
106
+ "weight_only_quant_matmul_plugin": null,
107
+ "quantize_per_token_plugin": false,
108
+ "quantize_tensor_plugin": false,
109
+ "moe_plugin": "float16",
110
+ "context_fmha": true,
111
+ "context_fmha_fp32_acc": false,
112
+ "paged_kv_cache": true,
113
+ "remove_input_padding": true,
114
+ "use_custom_all_reduce": true,
115
+ "multi_block_mode": false,
116
+ "enable_xqa": true,
117
+ "attention_qk_half_accumulation": false,
118
+ "tokens_per_block": 128,
119
+ "use_paged_context_fmha": false,
120
+ "use_context_fmha_for_generation": false,
121
+ "dense_context_fmha": false,
122
+ "pos_shift": false
123
+ }
124
+ }
125
+ }
rank0.engine ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf8c95a77a5f145ae1c11a3e06675998b45bf11fad62b667d704482d486dc49
3
+ size 13480095900
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "sp_model_kwargs": {},
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }