Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
 trtllm_checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+engine/rank0.engine filter=lfs diff=lfs merge=lfs -text
+engine/tokenizer.json filter=lfs diff=lfs merge=lfs -text

engine/chat_template.jinja

@@ -0,0 +1,3 @@
+{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] | trim + '
+
+' %}{% set messages = messages[1:] %}{% else %}{% set system_message = '' %}{% endif %}{{- bos_token + system_message}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '[INST]' + message['content'] | trim + '[/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] | trim + eos_token }}{% endif %}{% endfor %}

engine/config.json

@@ -0,0 +1,231 @@
+{
+    "model_type": "mistral",
+    "version": "1.1.0",
+    "pretrained_config": {
+        "mlp_bias": false,
+        "attn_bias": false,
+        "rotary_base": 1000000.0,
+        "rotary_scaling": null,
+        "residual_mlp": false,
+        "disable_weight_only_quant_plugin": false,
+        "moe": {
+            "num_experts": 0,
+            "shared_expert_intermediate_size": 0,
+            "top_k": 0,
+            "normalization_mode": null,
+            "sparse_mixer_epsilon": 0.01,
+            "tp_mode": 0,
+            "device_limited_n_group": 0,
+            "device_limited_topk_group": 0,
+            "device_limited_routed_scaling_factor": 1.0
+        },
+        "remove_duplicated_kv_heads": false,
+        "fc_after_embed": false,
+        "use_input_layernorm_in_first_layer": true,
+        "use_last_layernorm": true,
+        "layer_idx_offset": 0,
+        "embedding_multiplier": 1.0,
+        "attention_multiplier": 1.0,
+        "residual_multiplier": 1.0,
+        "output_multiplier_scale": 1.0,
+        "has_partial_lora_mask": false,
+        "architecture": "MistralForCausalLM",
+        "architectures": [
+            "MistralForCausalLM"
+        ],
+        "dtype": "bfloat16",
+        "vocab_size": 131072,
+        "hidden_size": 5120,
+        "num_hidden_layers": 40,
+        "num_attention_heads": 32,
+        "hidden_act": "silu",
+        "logits_dtype": "float16",
+        "norm_epsilon": 1e-05,
+        "runtime_defaults": null,
+        "position_embedding_type": "rope_gpt_neox",
+        "num_key_value_heads": 8,
+        "intermediate_size": 14336,
+        "max_position_embeddings": 1024000,
+        "mapping": {
+            "world_size": 1,
+            "gpus_per_node": 8,
+            "cp_size": 1,
+            "tp_size": 1,
+            "pp_size": 1,
+            "moe_tp_size": 1,
+            "moe_cluster_size": 1,
+            "moe_ep_size": 1,
+            "attn_tp_size": 1,
+            "attn_cp_size": 1,
+            "cp_config": {},
+            "auto_parallel": false,
+            "enable_attention_dp": false,
+            "enable_lm_head_tp_in_adp": false
+        },
+        "quantization": {
+            "quant_algo": "NVFP4",
+            "kv_cache_quant_algo": null,
+            "group_size": 16,
+            "smoothquant_val": 0.5,
+            "clamp_val": null,
+            "use_meta_recipe": false,
+            "has_zero_point": false,
+            "pre_quant_scale": false,
+            "exclude_modules": [
+                "lm_head"
+            ],
+            "mamba_ssm_cache_dtype": null
+        },
+        "use_parallel_embedding": true,
+        "embedding_sharding_dim": 0,
+        "head_size": 128,
+        "qk_layernorm": false,
+        "rotary_embedding_dim": 128,
+        "producer": {
+            "name": "modelopt",
+            "version": "0.37.0"
+        },
+        "share_embedding_table": false,
+        "bias": false,
+        "rotary_pct": 1.0,
+        "rank": 0,
+        "decoder": "mistral",
+        "rmsnorm": true,
+        "lm_head_bias": false,
+        "tie_word_embeddings": false
+    },
+    "build_config": {
+        "max_input_len": 1024,
+        "max_seq_len": 1024000,
+        "opt_batch_size": 8,
+        "max_batch_size": 2048,
+        "max_beam_width": 1,
+        "max_num_tokens": 8192,
+        "opt_num_tokens": 2048,
+        "max_prompt_embedding_table_size": 0,
+        "kv_cache_type": "PAGED",
+        "gather_context_logits": false,
+        "gather_generation_logits": false,
+        "strongly_typed": true,
+        "force_num_profiles": null,
+        "profiling_verbosity": "layer_names_only",
+        "enable_debug_output": false,
+        "max_draft_len": 0,
+        "speculative_decoding_mode": 1,
+        "use_refit": false,
+        "input_timing_cache": null,
+        "output_timing_cache": "model.cache",
+        "lora_config": {
+            "lora_dir": [],
+            "lora_ckpt_source": "hf",
+            "max_lora_rank": 64,
+            "lora_target_modules": [],
+            "trtllm_modules_to_hf_modules": {},
+            "max_loras": null,
+            "max_cpu_loras": null,
+            "swap_gate_up_proj_lora_b_weight": true
+        },
+        "auto_parallel_config": {
+            "world_size": 1,
+            "gpus_per_node": 8,
+            "cluster_key": "NVIDIA-RTX-PRO-6000-Blackwell-Max-Q-Workstation-Edition",
+            "cluster_info": {
+                "inter_node_bw_per_device": 25,
+                "intra_node_bw_per_device": 5,
+                "inter_node_latency": 10,
+                "intra_node_latency": 10,
+                "intra_node_sharp": false,
+                "inter_node_sharp": true,
+                "memory_bw": 1792,
+                "memory_budget_per_device": 95,
+                "math_throughput": {
+                    "int4": 0,
+                    "int8": 0,
+                    "fp8": 0,
+                    "float16": 0,
+                    "bfloat16": 0,
+                    "float32": 0
+                },
+                "memory_efficiency": 1.0,
+                "math_efficiency": 1.0,
+                "communication_efficiency": 1.0
+            },
+            "sharding_cost_model": "alpha_beta",
+            "comm_cost_model": "alpha_beta",
+            "enable_pipeline_parallelism": false,
+            "enable_shard_unbalanced_shape": false,
+            "enable_shard_dynamic_shape": false,
+            "enable_reduce_scatter": true,
+            "builder_flags": null,
+            "debug_mode": false,
+            "infer_shape": true,
+            "validation_mode": false,
+            "same_buffer_io": {
+                "past_key_value_(\\d+)": "present_key_value_\\1"
+            },
+            "same_spec_io": {},
+            "sharded_io_allowlist": [
+                "past_key_value_\\d+",
+                "present_key_value_\\d*"
+            ],
+            "fill_weights": false,
+            "parallel_config_cache": null,
+            "profile_cache": null,
+            "dump_path": null,
+            "debug_outputs": []
+        },
+        "weight_sparsity": false,
+        "weight_streaming": false,
+        "plugin_config": {
+            "dtype": "bfloat16",
+            "bert_attention_plugin": "auto",
+            "gpt_attention_plugin": "auto",
+            "gemm_plugin": "nvfp4",
+            "explicitly_disable_gemm_plugin": false,
+            "gemm_swiglu_plugin": null,
+            "fp8_rowwise_gemm_plugin": null,
+            "qserve_gemm_plugin": null,
+            "identity_plugin": null,
+            "nccl_plugin": null,
+            "lora_plugin": null,
+            "dora_plugin": false,
+            "weight_only_groupwise_quant_matmul_plugin": null,
+            "weight_only_quant_matmul_plugin": null,
+            "smooth_quant_plugins": true,
+            "smooth_quant_gemm_plugin": null,
+            "layernorm_quantization_plugin": null,
+            "rmsnorm_quantization_plugin": null,
+            "quantize_per_token_plugin": false,
+            "quantize_tensor_plugin": false,
+            "moe_plugin": "auto",
+            "mamba_conv1d_plugin": "auto",
+            "low_latency_gemm_plugin": null,
+            "low_latency_gemm_swiglu_plugin": null,
+            "gemm_allreduce_plugin": null,
+            "context_fmha": true,
+            "bert_context_fmha_fp32_acc": false,
+            "paged_kv_cache": true,
+            "remove_input_padding": true,
+            "norm_quant_fusion": false,
+            "reduce_fusion": false,
+            "user_buffer": false,
+            "tokens_per_block": 32,
+            "use_paged_context_fmha": true,
+            "use_fp8_context_fmha": false,
+            "fuse_fp4_quant": false,
+            "multiple_profiles": false,
+            "paged_state": false,
+            "streamingllm": false,
+            "manage_weights": false,
+            "use_fused_mlp": true,
+            "pp_reduce_scatter": false
+        },
+        "use_strip_plan": false,
+        "max_encoder_input_len": 1024,
+        "monitor_memory": false,
+        "use_mrope": false
+    },
+    "architectures": [
+        "MistralForCausalLM"
+    ]
+}

engine/rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40bd4659c4be35116f97f076b64ba49be4970eeaee517c8d7c782eff734cc6ba
+size 9360956092

engine/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

engine/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8771d3c14b4206fd6b54c60d037eeafce2f37382046c2369c36cd2edd2f099d7
+size 17078391