Initial model upload, add README and MLC config

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+library_name: mlc-llm
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+tags:
+- mlc-llm
+- web-llm
+---
+
+# Qwen2.5-0.5B-Instruct-q4f16_1-MLC
+
+This is the [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) model in MLC format `q4f16_1`.
+The model can be used for projects [MLC-LLM](https://github.com/mlc-ai/mlc-llm) and [WebLLM](https://github.com/mlc-ai/web-llm).
+
+## Demo App and Model Training
+**Model Training:** Detailed training procedures, dataset configurations, and curriculum learning stages used to fine-tune this model are documented in the [Individual Studies repository](https://github.com/BennyWang1007/Individual-studies)
+
+**Demo Application:** To explore the model's capabilities in a real-world mobile setup, refer to the companion app repository: [Individual Studies App](https://github.com/BennyWang1007/Individual-studies-app)
+
+## Example Usage
+
+Here are some examples of using this model in MLC LLM.
+Before running the examples, please install MLC LLM by following the [installation documentation](https://llm.mlc.ai/docs/install/mlc_llm.html#install-mlc-packages).
+
+### Chat
+
+In command line, run
+```bash
+mlc_llm chat HF://BennyWang/Qwen2.5-0.5B-Instruct-cl-24233news-5stg-v4-lr_adj-q4f16_1-MLC
+```
+
+### REST Server
+
+In command line, run
+```bash
+mlc_llm serve HF://BennyWang/Qwen2.5-0.5B-Instruct-cl-24233news-5stg-v4-lr_adj-q4f16_1-MLC
+```
+
+### Python API
+
+```python
+from mlc_llm import MLCEngine
+
+# Create engine
+model = "HF://BennyWang/Qwen2.5-0.5B-Instruct-cl-24233news-5stg-v4-lr_adj-q4f16_1-MLC"
+engine = MLCEngine(model)
+
+# Run chat completion in OpenAI API.
+for response in engine.chat.completions.create(
+    messages=[{"role": "user", "content": "What is the meaning of life?"}],
+    model=model,
+    stream=True,
+):
+    for choice in response.choices:
+        print(choice.delta.content, end="", flush=True)
+print("\n")
+
+engine.terminate()
+```
+
+## Documentation
+
+For more information on MLC LLM project, please visit our [documentation](https://llm.mlc.ai/docs/) and [GitHub repo](http://github.com/mlc-ai/mlc-llm).
+

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

mlc-chat-config.json

@@ -0,0 +1,83 @@
+{
+  "version": "0.1.0",
+  "model_type": "qwen2",
+  "quantization": "q4f16_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": 2048,
+    "prefill_chunk_size": 2048,
+    "tensor_parallel_shards": 1,
+    "head_dim": 64,
+    "dtype": "float32",
+    "max_batch_size": 128
+  },
+  "vocab_size": 151936,
+  "context_window_size": 2048,
+  "sliding_window_size": -1,
+  "prefill_chunk_size": 2048,
+  "attention_sink_size": -1,
+  "tensor_parallel_shards": 1,
+  "pipeline_parallel_stages": 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",
+    "added_tokens.json",
+    "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
+  ]
+}

params_shard_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77b5dc56cc985ffad5b00e0fa6a3e7ae339579b4e9454d51737e1179658e9f2a
+size 68067328

params_shard_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c585bd957fe7a5a61b1f10d6366e6ca5a20a0d9304526f27888bfc07abd1868
+size 33234176

params_shard_2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea289c3607c04385867eff58fe030b594617a2bdadda939add80de3c8604d0e
+size 33505280

params_shard_3.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ac6ef1fb86904053cb25c3ed28af3cd591bc42249d27c6b7be8ec67c5d5809
+size 33053696

params_shard_4.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3bb93a09294b5041265885fc138fd6acec152a8e853cca6716193e0a46b1454
+size 33020928

params_shard_5.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7991018f95b08502f83e4a197e67e199af7a7f4a73a3986f7f4ef90657576442
+size 29211648

params_shard_6.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb536f5ade24ce8ea13bfbafaa9c75d8d6063eda7afaf4a060910239aa8af70
+size 33297408

params_shard_7.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a19bb1f95ea49bc4dfbaca2eb4ed10ab166d5601e4178362de9097cec026834
+size 14605824

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab62901449b8e8e7c6e5142a52320b673dba2376aa119ed6830206f2de78bb20
+size 11422175

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}