del

config.json

@@ -1,54 +0,0 @@
-{
-  "builder_config": {
-    "gather_all_token_logits": false,
-    "hidden_act": "silu",
-    "hidden_size": 2048,
-    "int8": false,
-    "lora_target_modules": [],
-    "max_batch_size": 8,
-    "max_beam_width": 1,
-    "max_input_len": 2048,
-    "max_num_tokens": null,
-    "max_output_len": 512,
-    "max_position_embeddings": 2048,
-    "max_prompt_embedding_table_size": 0,
-    "name": "llama",
-    "num_heads": 32,
-    "num_kv_heads": 4,
-    "num_layers": 22,
-    "parallel_build": false,
-    "pipeline_parallel": 1,
-    "precision": "float16",
-    "quant_mode": 0,
-    "tensor_parallel": 1,
-    "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": false,
-    "paged_kv_cache": false,
-    "quantize_per_token_plugin": false,
-    "quantize_tensor_plugin": false,
-    "remove_input_padding": false,
-    "rmsnorm_plugin": false,
-    "rmsnorm_quantization_plugin": false,
-    "smooth_quant_gemm_plugin": false,
-    "tokens_per_block": 0,
-    "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
-  }
-}

mistral_float16_tp1_rank0.engine

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:43cfe9e96214a3e8edfb95d0bc3ff6543cb6952fec3d3c59c43ef3d4b125cd9a
-size 2202995884

special_tokens_map.json

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

tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723

tokenizer_config.json

@@ -1,42 +0,0 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": false,
-  "model_max_length": 2048,
-  "pad_token": "</s>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}