Initial commit

mlc-chat-config.json

@@ -0,0 +1,81 @@
+{
+  "version": "0.1.0",
+  "model_type": "qwen2",
+  "quantization": "q4f32_1",
+  "model_config": {
+    "hidden_act": "silu",
+    "hidden_size": 896,
+    "intermediate_size": 4864,
+    "num_attention_heads": 14,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "vocab_size": 151936,
+    "tie_word_embeddings": true,
+    "context_window_size": 32768,
+    "prefill_chunk_size": 2048,
+    "tensor_parallel_shards": 1,
+    "head_dim": 64,
+    "dtype": "float32",
+    "max_batch_size": 80
+  },
+  "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": 1.1,
+  "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}",
+    "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
+  ]
+}

params_shard_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcef4ca2b218e1afe003d72dd81f38b08be3137dae5e28006a5d340588ca4e99
+size 68067328

params_shard_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd7df5d90935fcd31e865529a112adcb434b6ac2a14dcac8d0b23cadb98e8fc
+size 33234176

params_shard_2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7762563b9de6fce45372b2e7585d2e61ecda069a02c8310e48fbb5b6ceb759
+size 33505280

params_shard_3.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78391bce63b798e2e204a5874116111a6cba76a4e399807ae6de934927bd3676
+size 33053696

params_shard_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3773caa2fceac237fd9f8917e08fb6363999dafd9de52e75798d55acbb6ad79c
+size 33020928

params_shard_5.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2dc88af78a0364a5f7e32237746f6a213bb2a6d457f35851629dce271f42d36
+size 29211648

params_shard_6.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9747ccba2c1174e8983a50ccf067f733e4e6dee2045d1d38fbc7b79db1b73e54
+size 33297408

params_shard_7.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b291d01bf87d99cbac6f9a61d07d1da32a5097715247a606b84e5fafa399e538
+size 14605824

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'] + '<|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
+}