add model

mlc-chat-config.json

@@ -0,0 +1,76 @@
+{
+  "model_type": "qwen2",
+  "quantization": "q4f16_1",
+  "model_config": {
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "intermediate_size": 5504,
+    "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,
+    "context_window_size": 2048,
+    "prefill_chunk_size": 2048,
+    "tensor_parallel_shards": 1,
+    "head_dim": 128,
+    "dtype": "float32"
+  },
+  "vocab_size": 151936,
+  "context_window_size": 2048,
+  "sliding_window_size": -1,
+  "prefill_chunk_size": 2048,
+  "attention_sink_size": -1,
+  "tensor_parallel_shards": 1,
+  "mean_gen_len": 128,
+  "max_gen_len": 512,
+  "shift_fill_factor": 0.3,
+  "temperature": 0.7,
+  "presence_penalty": 0.0,
+  "frequency_penalty": 0.0,
+  "repetition_penalty": 1.1,
+  "top_p": 0.8,
+  "conv_template": {
+    "name": "chatml",
+    "system_template": "<|im_start|>system\n{system_message}",
+    "system_message": "A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.",
+    "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
+  ],
+  "tokenizer_files": [
+    "tokenizer.json",
+    "vocab.json",
+    "merges.txt",
+    "tokenizer_config.json"
+  ],
+  "version": "0.1.0"
+}

params_shard_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd1b492861cd32161e45b42c370bc202604ad3d4914de99b74ae0c5b5bdd73b9
+size 155582464

params_shard_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba71642f404e31c7821bb935142fb3b101295fcfdffd947f0d8f1a2c136bc41
+size 155582464

params_shard_10.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c51b727b89b74457e87a841cb5abd0d76a7bb212f334a71f52ed284f5bfec92
+size 28479488

params_shard_11.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c575e577339dc86e3af82eecfeee32febf6ef8badf0436a9db3edc4c9ee5090
+size 28479488

params_shard_12.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a45e11f9e8d29becd96b6e0ad2e270248da6ac029e8af14e7360d697a257d1
+size 28479488

params_shard_13.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5ca17b12e6b1ef4e51eca8e3dc311a275550cfe2d9a4f03a17f40ee2ab2bcf
+size 28479488

params_shard_14.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7f3e314224f0a88726a25d0265928552141f9a3a8021da0f98a524377a72a49
+size 28479488

params_shard_15.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44eeacaed25dd74c3e400c4ff3af25d01f8c1bd0b9e8853eb6e74d41203730bc
+size 28479488

params_shard_16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dffcdd86bdd1c124f722c36dd9b5816def620221ba7584b2f63140e12aa7987
+size 28479488

params_shard_17.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ea9861c09fb61b62cc8d4a4e874a61faec76e32db4bec16a3decb8ddea535f
+size 28479488

params_shard_18.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f11754616b0e94503129911760033d4ea9353c06dcf1d926b64d9e273356f31
+size 28479488

params_shard_19.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45c304b41bdb2531740b05a60e3eaa907b15b6bb94f9690692b7f131316571c
+size 28479488

params_shard_2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d28e00d872e03fdca57076746f2440a921e43d383f0174808cb2319cfe5c8f
+size 19447808

params_shard_20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1732ec8dc2adb1b497e3af25e72a7f2956a2b29d598980436948455b5135b0ea
+size 28479488

params_shard_21.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b147f82475b45297f198c829098cddf9e81b9d96d73effd295f4573ef3f007
+size 28479488

params_shard_22.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455feea485a81cec70f0434a5f0277ab97ff225c06312394da5764b369fa8092
+size 28479488

params_shard_23.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:587e663ca36237024e933c92b70c06f690f22733134976d79776a5b33602b589
+size 28479488

params_shard_24.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:019209b6fbed3e7824842ee6d83932fa6d5b8ca077716bfaf9c9a8e290869371
+size 28479488

params_shard_25.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68afdcd0c2e1d82c2afef26775f40b8913ac4aa6d4b2de3b8ac4fd2b7328d67
+size 28479488

params_shard_26.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cbc1ceaa106f186fcb6496da875fd1c68dcf7b10d7caa0bb0612841387ccc2d
+size 28479488

params_shard_27.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f17bbe1bb5469f3aa0be308a4cb82387503794a07a1a6e8edec6494c9fab0fc
+size 22138880

params_shard_3.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:832107ad5e073acb71104edefa71ab794e0e98be3a616d335f49629008129d15
+size 25792512

params_shard_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3141431b8d9700a9ede0d1a2a35e90d62665caf8e4c442473b9f194c71ae5f
+size 28479488

params_shard_5.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7980c3fe56d552213edfd64a8535addfa44cdbe4d4b5aebc24c543bda0da5111
+size 28479488

params_shard_6.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe9412d22a2ab7486606867b3cb0fc4c98ff76a0f1e1e20efd426da9e11f6994
+size 28479488

params_shard_7.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba65b22109ad65b40c7b328ce9eb5c60c5ef572392a8fbce7b63f2358bd4598
+size 28479488

params_shard_8.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b69460f5a8608038712a9a5b72130b8a18179ffc4229e461b04c05cf1300981d
+size 28479488

params_shard_9.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0421fd7114e31ab89b781243f495c8fd53384f26efa014809ad4b02fa4f4dfb6
+size 28479488

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|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
+}