Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+rank0.engine filter=lfs diff=lfs merge=lfs -text
+rank1.engine filter=lfs diff=lfs merge=lfs -text
+rank2.engine filter=lfs diff=lfs merge=lfs -text
+rank3.engine filter=lfs diff=lfs merge=lfs -text
+rank4.engine filter=lfs diff=lfs merge=lfs -text
+rank5.engine filter=lfs diff=lfs merge=lfs -text
+rank6.engine filter=lfs diff=lfs merge=lfs -text
+rank7.engine filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,112 @@
+{
+    "version": "0.9.0.dev2024022000",
+    "pretrained_config": {
+        "architecture": "MixtralForCausalLM",
+        "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": "swiglu",
+        "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": 8,
+            "tp_size": 8,
+            "pp_size": 1
+        },
+        "kv_dtype": "float16",
+        "max_lora_rank": 64,
+        "rotary_base": 1000000.0,
+        "rotary_scaling": null,
+        "moe_num_experts": 8,
+        "moe_top_k": 2,
+        "moe_tp_mode": 1,
+        "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": 4000,
+        "max_output_len": 1000,
+        "max_batch_size": 32,
+        "max_beam_width": 1,
+        "max_num_tokens": 128000,
+        "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": "float16",
+            "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
+        }
+    }
+}

rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c788b10bbf1e7fc208755f79de0996423d6a7f68d9e59258b86cb0aa7003e599
+size 11910698012

rank1.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e318354c22268b74953008a44dcb19f9afc38293181e919c18e5df65a99240f
+size 11910699596

rank2.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:385e9d02247e8800b70a35e2319eb04e0021b487733a16372460b734dc36d88f
+size 11910698012

rank3.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5456e0a0af135e9912021439c6bf822265242bfb12c1f16ebc7feecb8126f336
+size 11910698012

rank4.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f4fbf06628d5ecc36bf4890c445097cbd0d0529a7d259fd158a2f70386d7d59
+size 11910698012

rank5.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19442cbb066adc8a18f813b7c2bd61dd20d5236d3ea70c7969be4cb2f4f1bd02
+size 11910723428

rank6.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690c52fef8f4a954d8b65b394790ed78ab96b08f273a98d37bd262bafbbaad2a
+size 11910725012

rank7.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea347ac4b6523fd9c75181e1ee1c46608a7048b9b00e4ed78d13d3c5f2be05eb
+size 11910723428