Upload folder using huggingface_hub

README.md

@@ -0,0 +1,6 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B-Chat
+---
+
+[MLC](https://llm.mlc.ai/) version of [Qwen/Qwen1.5-MoE-A2.7B-Chat](https://huggingface.co/Qwen/Qwen1.5-MoE-A2.7B-Chat), using `q4f16_1` quantization.
+

mlc-chat-config.json

@@ -0,0 +1,87 @@
+{
+  "version": "0.1.0",
+  "model_type": "qwen2_moe",
+  "quantization": "q4f16_1",
+  "model_config": {
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "intermediate_size": 5632,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 16,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "vocab_size": 151936,
+    "tie_word_embeddings": false,
+    "context_window_size": 32768,
+    "prefill_chunk_size": 2048,
+    "tensor_parallel_shards": 1,
+    "head_dim": 128,
+    "dtype": "float32",
+    "max_batch_size": 80,
+    "moe_intermediate_size": 1408,
+    "shared_expert_intermediate_size": 5632,
+    "num_experts_per_tok": 4,
+    "num_experts": 60,
+    "decoder_sparse_step": 1,
+    "norm_topk_prob": false
+  },
+  "vocab_size": 151936,
+  "context_window_size": 32768,
+  "sliding_window_size": -1,
+  "prefill_chunk_size": 2048,
+  "attention_sink_size": -1,
+  "tensor_parallel_shards": 1,
+  "temperature": 0.7,
+  "presence_penalty": 0.0,
+  "frequency_penalty": 0.0,
+  "repetition_penalty": 1.05,
+  "top_p": 0.8,
+  "tokenizer_files": [
+    "tokenizer.json",
+    "vocab.json",
+    "merges.txt",
+    "tokenizer_config.json"
+  ],
+  "tokenizer_info": {
+    "token_postproc_method": "byte_level",
+    "prepend_space_in_encode": false,
+    "strip_space_in_decode": false
+  },
+  "conv_template": {
+    "name": "chatml",
+    "system_template": "<|im_start|>system\n{system_message}<|im_end|>\n",
+    "system_message": "A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.",
+    "system_prefix_token_ids": null,
+    "add_role_after_system_message": true,
+    "roles": {
+      "user": "<|im_start|>user",
+      "assistant": "<|im_start|>assistant"
+    },
+    "role_templates": {
+      "user": "{user_message}",
+      "assistant": "{assistant_message}",
+      "tool": "{tool_message}"
+    },
+    "messages": [],
+    "seps": [
+      "<|im_end|>\n"
+    ],
+    "role_content_sep": "\n",
+    "role_empty_sep": "\n",
+    "stop_str": [
+      "<|im_end|>"
+    ],
+    "stop_token_ids": [
+      2
+    ],
+    "function_string": "",
+    "use_function_calling": false
+  },
+  "pad_token_id": 151643,
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ]
+}

model.wasm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416ecde813854a5f7df0a11b3fcb659f4909bdd4816f304099e28f9841b50acb
+size 5150442

params_shard_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc981f3ce907322a6dc70b4f84b9f1e515cc0fc46e28bb076825168c9643744d
+size 155582464

params_shard_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2de82c66adf507a3971269303a6d7b3e84f18440615f51c7710cc278c00bee
+size 25939968

params_shard_2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d69e4060d5905a644777f1d38b9d7e04fab09a3c18e44ccfa0ce946a0d94ce
+size 155582464

params_shard_3.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee278b25bfb80b70e128bb41248c49bb208bd9d187ea7636b0a0675c7260af35
+size 86507520

params_shard_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea186491e043a27e3c2917f87b68b7c3bff960c7cd38dd6a8be9e8d73f5e00b2
+size 32440320

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", 
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
+