Upload folder using huggingface_hub

.gitattributes

@@ -49,3 +49,4 @@ mistral-7b-instruct-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
 mistral-7b-instruct-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 mistral-7b-instruct-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
 mistral-7b-instruct-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+mistral_float16_tp1_rank0.engine filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,54 @@
+{
+  "builder_config": {
+    "gather_all_token_logits": false,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "int8": true,
+    "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": 32768,
+    "max_prompt_embedding_table_size": 0,
+    "name": "llama",
+    "num_heads": 32,
+    "num_kv_heads": 8,
+    "num_layers": 32,
+    "parallel_build": false,
+    "pipeline_parallel": 1,
+    "precision": "float16",
+    "quant_mode": 33,
+    "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": true,
+    "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": "float16",
+    "weight_only_quant_matmul_plugin": false
+  }
+}

mistral_float16_tp1_rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9f31e878f3a698062f1883e3a5b6f7a2db4a4b344d0b156ceea7c7c54fc2b5
+size 3935996836

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}