Upload folder using huggingface_hub

.gitattributes

@@ -46,3 +46,4 @@ tinyllama-1.1b-chat-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 tinyllama-1.1b-chat-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
 tinyllama-1.1b-chat-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 mistral_float16_tp1_rank0.engine filter=lfs diff=lfs merge=lfs -text
+rank0.engine filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,112 @@
+{
+    "version": "0.8.0",
+    "pretrained_config": {
+        "architecture": "LlamaForCausalLM",
+        "dtype": "float16",
+        "logits_dtype": "float32",
+        "vocab_size": 32000,
+        "max_position_embeddings": 2048,
+        "hidden_size": 2048,
+        "num_hidden_layers": 22,
+        "num_attention_heads": 32,
+        "num_key_value_heads": 4,
+        "head_size": 64,
+        "hidden_act": "silu",
+        "intermediate_size": 5632,
+        "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": 1,
+            "tp_size": 1,
+            "pp_size": 1
+        },
+        "kv_dtype": "float16",
+        "max_lora_rank": 64,
+        "rotary_base": 10000.0,
+        "rotary_scaling": null,
+        "moe_num_experts": 0,
+        "moe_top_k": 0,
+        "moe_tp_mode": 2,
+        "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": [
+                "lm_head"
+            ],
+            "sq_use_plugin": false
+        }
+    },
+    "build_config": {
+        "max_input_len": 1024,
+        "max_output_len": 1024,
+        "max_batch_size": 1,
+        "max_beam_width": 1,
+        "max_num_tokens": 1024,
+        "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,
+        "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": null,
+            "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,
+            "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:fc60fcc4e7ce7939b2ae4c1773920553d16d24ef9cce678909e8a3555dd9c70e
+size 2202329596

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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

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

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+}