Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- config.json +125 -0
- rank0.engine +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
.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": "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": 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": 2048,
|
51 |
+
"max_output_len": 2048,
|
52 |
+
"max_batch_size": 64,
|
53 |
+
"max_beam_width": 1,
|
54 |
+
"max_num_tokens": 131072,
|
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": "H100-PCIe",
|
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 sha256:47382cf4c5c0d83051cdfd45ac3e83bccf62855505c10364ee8e5fe2609c18bd
|
3 |
+
size 14486760308
|
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 |
+
}
|