Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,8 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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_tp8_rank2.engine filter=lfs diff=lfs merge=lfs -text
+llama_float16_tp8_rank3.engine filter=lfs diff=lfs merge=lfs -text
+llama_float16_tp8_rank4.engine filter=lfs diff=lfs merge=lfs -text
+llama_float16_tp8_rank5.engine filter=lfs diff=lfs merge=lfs -text
+llama_float16_tp8_rank6.engine filter=lfs diff=lfs merge=lfs -text
+llama_float16_tp8_rank7.engine filter=lfs diff=lfs merge=lfs -text
+llama_float16_tp8_rank0.engine filter=lfs diff=lfs merge=lfs -text
+llama_float16_tp8_rank1.engine filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,57 @@
+{
+  "builder_config": {
+    "autopp_config": null,
+    "gather_context_logits": false,
+    "gather_generation_logits": false,
+    "hidden_act": "swiglu",
+    "hidden_size": 4096,
+    "int8": false,
+    "lora_target_modules": null,
+    "max_batch_size": 8,
+    "max_beam_width": 1,
+    "max_input_len": 2048,
+    "max_num_tokens": null,
+    "max_output_len": 512,
+    "max_position_embeddings": 32768,
+    "max_prompt_embedding_table_size": 0,
+    "mlp_hidden_size": 14336,
+    "name": "llama",
+    "num_heads": 32,
+    "num_kv_heads": 8,
+    "num_layers": 32,
+    "parallel_build": true,
+    "pipeline_parallel": 1,
+    "precision": "float16",
+    "quant_mode": 0,
+    "tensor_parallel": 8,
+    "use_refit": false,
+    "vocab_size": 32000
+  },
+  "plugin_config": {
+    "attention_qk_half_accumulation": false,
+    "bert_attention_plugin": false,
+    "context_fmha_type": 1,
+    "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": 128,
+    "use_context_fmha_for_generation": false,
+    "use_custom_all_reduce": false,
+    "use_paged_context_fmha": false,
+    "weight_only_groupwise_quant_matmul_plugin": false,
+    "weight_only_quant_matmul_plugin": false
+  }
+}

llama_float16_tp8_rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c18242a30cf3ea8da41fda8946068b6793083045a04d88927f9de314725f5a
+size 11909565388

llama_float16_tp8_rank1.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4729e570684556a1585735880d130f094f1a149d77cd5532ab162ccf9bd2c874
+size 11909565580

llama_float16_tp8_rank2.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db5f0f612927f99293610e252266996310b4be3c4bc7cb7d95e9ebea80a0b1a6
+size 11909566348

llama_float16_tp8_rank3.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dcf77fa9dffe98883a4ee814307693d6237890414d0c1bfad6419da8c991d27
+size 11909544580

llama_float16_tp8_rank4.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e37de9a27b73e96fa4c30684649c12c889cc5626a6df7753602c17d5b785231
+size 11909545540

llama_float16_tp8_rank5.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e295ab4ce7de481d261de5ff7cb02c634b6f8cdd405f3d69dd02e0b8d917ce99
+size 11909545348

llama_float16_tp8_rank6.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0290823dd2c5619089246e8228ddfbd39ece550769f68edc337ceeb8172ea75d
+size 11909565580

llama_float16_tp8_rank7.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd2412281fc802c6386682f2573609cfb03cf70ed788154679326237029911c
+size 11909566348