Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ 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
+llama_float16_tp4_rank0.engine filter=lfs diff=lfs merge=lfs -text
+llama_float16_tp4_rank1.engine filter=lfs diff=lfs merge=lfs -text
+llama_float16_tp4_rank2.engine filter=lfs diff=lfs merge=lfs -text
+llama_float16_tp4_rank3.engine filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,51 @@
+{
+  "builder_config": {
+    "gather_all_token_logits": false,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "int8": false,
+    "max_batch_size": 8,
+    "max_beam_width": 1,
+    "max_input_len": 3800,
+    "max_num_tokens": null,
+    "max_output_len": 250,
+    "max_position_embeddings": 4096,
+    "max_prompt_embedding_table_size": 0,
+    "name": "llama",
+    "num_heads": 64,
+    "num_kv_heads": 8,
+    "num_layers": 80,
+    "parallel_build": false,
+    "pipeline_parallel": 1,
+    "precision": "float16",
+    "quant_mode": 0,
+    "tensor_parallel": 4,
+    "use_refit": false,
+    "vocab_size": 32000
+  },
+  "plugin_config": {
+    "attention_qk_half_accumulation": false,
+    "bert_attention_plugin": false,
+    "context_fmha_type": 0,
+    "gemm_plugin": "float16",
+    "gpt_attention_plugin": "float16",
+    "identity_plugin": false,
+    "layernorm_plugin": false,
+    "layernorm_quantization_plugin": false,
+    "lookup_plugin": false,
+    "lora_plugin": false,
+    "multi_block_mode": false,
+    "nccl_plugin": "float16",
+    "paged_kv_cache": true,
+    "quantize_per_token_plugin": false,
+    "quantize_tensor_plugin": false,
+    "remove_input_padding": true,
+    "rmsnorm_plugin": false,
+    "rmsnorm_quantization_plugin": false,
+    "smooth_quant_gemm_plugin": false,
+    "tokens_per_block": 64,
+    "use_custom_all_reduce": false,
+    "weight_only_groupwise_quant_matmul_plugin": false,
+    "weight_only_quant_matmul_plugin": false
+  }
+}

llama_float16_tp4_rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f6fe921a056a34078ff3b46e9c494db317d7f219627f83027720f0696b816d
+size 34892901708

llama_float16_tp4_rank1.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a0a03a16e58a62c7420d134c5c29990ca2f9fed025d25bf09eb2724ad66168
+size 34892901708

llama_float16_tp4_rank2.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3210de777a8c4ec123875117213c0aa3dae702fb7f4d7755b9b18a6e39a3d188
+size 34892901708

llama_float16_tp4_rank3.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aae607373b1f020414273cccc2a0bb5b7389e4902bcf2455fafbb78d2c8bcf2
+size 34892901708