sumo43 commited on
Commit
6cef119
1 Parent(s): 5de0757

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
37
+ rank1.engine filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.8.0",
3
+ "pretrained_config": {
4
+ "architecture": "MistralForCausalLM",
5
+ "dtype": "float16",
6
+ "logits_dtype": "float32",
7
+ "vocab_size": 32000,
8
+ "max_position_embeddings": 32768,
9
+ "hidden_size": 4096,
10
+ "num_hidden_layers": 32,
11
+ "num_attention_heads": 32,
12
+ "num_key_value_heads": 8,
13
+ "head_size": 128,
14
+ "hidden_act": "silu",
15
+ "intermediate_size": 14336,
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": 2,
24
+ "tp_size": 2,
25
+ "pp_size": 1
26
+ },
27
+ "kv_dtype": "float16",
28
+ "max_lora_rank": 64,
29
+ "rotary_base": 10000.0,
30
+ "rotary_scaling": null,
31
+ "moe_num_experts": 0,
32
+ "moe_top_k": 0,
33
+ "moe_tp_mode": 2,
34
+ "moe_normalization_mode": 1,
35
+ "enable_pos_shift": false,
36
+ "dense_context_fmha": false,
37
+ "lora_target_modules": null,
38
+ "hf_modules_to_trtllm_modules": {
39
+ "q_proj": "attn_q",
40
+ "k_proj": "attn_k",
41
+ "v_proj": "attn_v",
42
+ "o_proj": "attn_dense",
43
+ "gate_proj": "mlp_h_to_4h",
44
+ "down_proj": "mlp_4h_to_h",
45
+ "up_proj": "mlp_gate"
46
+ },
47
+ "trtllm_modules_to_hf_modules": {
48
+ "attn_q": "q_proj",
49
+ "attn_k": "k_proj",
50
+ "attn_v": "v_proj",
51
+ "attn_dense": "o_proj",
52
+ "mlp_h_to_4h": "gate_proj",
53
+ "mlp_4h_to_h": "down_proj",
54
+ "mlp_gate": "up_proj"
55
+ },
56
+ "disable_weight_only_quant_plugin": false,
57
+ "mlp_bias": false,
58
+ "attn_bias": false,
59
+ "quantization": {
60
+ "quant_algo": null,
61
+ "kv_cache_quant_algo": null,
62
+ "group_size": 128,
63
+ "has_zero_point": false,
64
+ "pre_quant_scale": false,
65
+ "exclude_modules": [
66
+ "lm_head"
67
+ ],
68
+ "sq_use_plugin": false
69
+ }
70
+ },
71
+ "build_config": {
72
+ "max_input_len": 1024,
73
+ "max_output_len": 1024,
74
+ "max_batch_size": 1,
75
+ "max_beam_width": 1,
76
+ "max_num_tokens": 1024,
77
+ "max_prompt_embedding_table_size": 0,
78
+ "gather_context_logits": false,
79
+ "gather_generation_logits": false,
80
+ "strongly_typed": false,
81
+ "builder_opt": null,
82
+ "profiling_verbosity": "layer_names_only",
83
+ "enable_debug_output": false,
84
+ "plugin_config": {
85
+ "bert_attention_plugin": "float16",
86
+ "gpt_attention_plugin": "float16",
87
+ "gemm_plugin": null,
88
+ "smooth_quant_gemm_plugin": null,
89
+ "identity_plugin": null,
90
+ "layernorm_quantization_plugin": null,
91
+ "rmsnorm_quantization_plugin": null,
92
+ "nccl_plugin": "float16",
93
+ "lookup_plugin": null,
94
+ "lora_plugin": null,
95
+ "weight_only_groupwise_quant_matmul_plugin": null,
96
+ "weight_only_quant_matmul_plugin": null,
97
+ "quantize_per_token_plugin": false,
98
+ "quantize_tensor_plugin": false,
99
+ "context_fmha": true,
100
+ "context_fmha_fp32_acc": false,
101
+ "paged_kv_cache": true,
102
+ "remove_input_padding": true,
103
+ "use_custom_all_reduce": true,
104
+ "multi_block_mode": false,
105
+ "enable_xqa": true,
106
+ "attention_qk_half_accumulation": false,
107
+ "tokens_per_block": 128,
108
+ "use_paged_context_fmha": false,
109
+ "use_context_fmha_for_generation": false
110
+ }
111
+ }
112
+ }
rank0.engine ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017677367ddaa5c10316137098aaf0f24fb64c398e0a3334c47e08e64c2f6d9f
3
+ size 7385161132
rank1.engine ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd55edf6678f593b9119295423a29e3e7c60a32ddefff3d231a7e7466534621f
3
+ size 7384522732
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
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
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }