Hugging Face's logo

aspctu
/
llama3-8b-instruct-bs64-8000-8000

Transformers
Inference Endpoints
Model card Files Community
llama3-8b-instruct-bs64-8000-8000
File size: 3,814 Bytes 
f2da9cb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
 
{
    "version": "0.9.0.dev2024022000",
    "pretrained_config": {
        "architecture": "LlamaForCausalLM",
        "dtype": "float16",
        "logits_dtype": "float16",
        "vocab_size": 128256,
        "max_position_embeddings": 8192,
        "hidden_size": 4096,
        "num_hidden_layers": 32,
        "num_attention_heads": 32,
        "num_key_value_heads": 8,
        "head_size": 128,
        "hidden_act": "silu",
        "intermediate_size": 14336,
        "norm_epsilon": 1e-05,
        "position_embedding_type": "rope_gpt_neox",
        "use_prompt_tuning": false,
        "use_parallel_embedding": false,
        "embedding_sharding_dim": 0,
        "share_embedding_table": false,
        "mapping": {
            "world_size": 1,
            "tp_size": 1,
            "pp_size": 1
        },
        "kv_dtype": "float16",
        "max_lora_rank": 64,
        "rotary_base": 10000.0,
        "rotary_scaling": null,
        "moe_num_experts": 0,
        "moe_top_k": 0,
        "moe_tp_mode": 2,
        "moe_normalization_mode": 1,
        "enable_pos_shift": false,
        "dense_context_fmha": false,
        "lora_target_modules": null,
        "hf_modules_to_trtllm_modules": {
            "q_proj": "attn_q",
            "k_proj": "attn_k",
            "v_proj": "attn_v",
            "o_proj": "attn_dense",
            "gate_proj": "mlp_h_to_4h",
            "down_proj": "mlp_4h_to_h",
            "up_proj": "mlp_gate"
        },
        "trtllm_modules_to_hf_modules": {
            "attn_q": "q_proj",
            "attn_k": "k_proj",
            "attn_v": "v_proj",
            "attn_dense": "o_proj",
            "mlp_h_to_4h": "gate_proj",
            "mlp_4h_to_h": "down_proj",
            "mlp_gate": "up_proj"
        },
        "disable_weight_only_quant_plugin": false,
        "mlp_bias": false,
        "attn_bias": false,
        "quantization": {
            "quant_algo": null,
            "kv_cache_quant_algo": null,
            "group_size": 128,
            "has_zero_point": false,
            "pre_quant_scale": false,
            "exclude_modules": null,
            "sq_use_plugin": false
        }
    },
    "build_config": {
        "max_input_len": 8192,
        "max_output_len": 8192,
        "max_batch_size": 64,
        "max_beam_width": 1,
        "max_num_tokens": null,
        "max_prompt_embedding_table_size": 0,
        "gather_context_logits": false,
        "gather_generation_logits": false,
        "strongly_typed": false,
        "builder_opt": null,
        "profiling_verbosity": "layer_names_only",
        "enable_debug_output": false,
        "max_draft_len": 0,
        "plugin_config": {
            "bert_attention_plugin": "float16",
            "gpt_attention_plugin": "float16",
            "gemm_plugin": "float16",
            "smooth_quant_gemm_plugin": null,
            "identity_plugin": null,
            "layernorm_quantization_plugin": null,
            "rmsnorm_quantization_plugin": null,
            "nccl_plugin": null,
            "lookup_plugin": null,
            "lora_plugin": null,
            "weight_only_groupwise_quant_matmul_plugin": null,
            "weight_only_quant_matmul_plugin": null,
            "quantize_per_token_plugin": false,
            "quantize_tensor_plugin": false,
            "moe_plugin": "float16",
            "context_fmha": true,
            "context_fmha_fp32_acc": false,
            "paged_kv_cache": true,
            "remove_input_padding": true,
            "use_custom_all_reduce": true,
            "multi_block_mode": false,
            "enable_xqa": true,
            "attention_qk_half_accumulation": false,
            "tokens_per_block": 128,
            "use_paged_context_fmha": false,
            "use_context_fmha_for_generation": false
        }
    }
}