Upload compiled-model/config.json with huggingface_hub

compiled-model/config.json

@@ -0,0 +1,115 @@
+{
+    "version": "0.8.0.dev2024013000",
+    "pretrained_config": {
+        "architecture": "MistralForCausalLM",
+        "dtype": "float16",
+        "logits_dtype": "float32",
+        "vocab_size": 32000,
+        "max_position_embeddings": 32768,
+        "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_config": {
+            "num_experts": 0,
+            "top_k": 0,
+            "tp_mode": 2,
+            "normalization_mode": 1
+        },
+        "moe_num_experts": 0,
+        "moe_top_k": 0,
+        "moe_tp_mode": 2,
+        "moe_normalization_mode": 1,
+        "use_fused_mlp": false,
+        "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
+        }
+    },
+    "build_config": {
+        "max_input_len": 32256,
+        "max_output_len": 1024,
+        "max_batch_size": 1,
+        "max_beam_width": 1,
+        "max_num_tokens": 32256,
+        "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",
+        "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,
+            "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
+        }
+    }
+}