Update README.md

README.md

@@ -6,4 +6,99 @@ language:
 base_model:
 - Qwen/Qwen3-4B
 pipeline_tag: text-generation
----
+---
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64633ebb39359568c63b52ad/r5EnnbDV6eGQQBeNBHu7K.png)
+
+### Model Details
+- **Name**: CarrotAI/Rabbit3-Ko-4B
+- **Version**: 4B Instruct
+- **Base Model**: Qwen/Qwen3-4B
+- **Languages**: Korean, English
+- **Model Type**: Large Language Model (Instruction-tuned)
+
+
+### Score
+
+|      Tasks       |Version|     Filter     |n-shot|        Metric         |   |Value |   |Stderr|
+|------------------|-------|----------------|-----:|-----------------------|---|-----:|---|------|
+|gsm8k             |      3|flexible-extract|     5|exact_match            |↑  |0.8400|±  |0.0101|
+|                  |       |strict-match    |     5|exact_match            |↑  |0.8378|±  |0.0102|
+|hrm8k             |    N/A|                |      |                       |   |      |   |      |
+| - hrm8k_gsm8k    |      1|none            |     0|exact_match            |↑  |0.8196|±  |0.0106|
+| - hrm8k_ksm      |      1|none            |     0|exact_match            |↑  |0.0511|±  |0.0058|
+| - hrm8k_math     |      1|none            |     0|exact_match            |↑  |0.5539|±  |0.0093|
+| - hrm8k_mmmlu    |      1|none            |     0|exact_match            |↑  |0.5362|±  |0.0230|
+| - hrm8k_omni_math|      1|none            |     0|exact_match            |↑  |0.1812|±  |0.0088|
+|ifeval            |      4|none            |     0|inst_level_loose_acc   |↑  |0.8753|±  |   N/A|
+|                  |       |none            |     0|inst_level_strict_acc  |↑  |0.8609|±  |   N/A|
+|                  |       |none            |     0|prompt_level_loose_acc |↑  |0.8244|±  |0.0164|
+|                  |       |none            |     0|prompt_level_strict_acc|↑  |0.8078|±  |0.0170|
+
+
+|Groups|Version|Filter|n-shot| Metric |   |Value |   |Stderr|
+|------|------:|------|------|--------|---|-----:|---|------|
+|haerae|      1|none  |      |acc     |↑  |0.6654|±  |0.0140|
+|      |       |none  |      |acc_norm|↑  |0.6654|±  |0.0140|
+|kobest|      1|none  |      |acc     |↑  |0.7768|±  |0.0057|
+|      |       |none  |      |acc_norm|↑  |0.5880|±  |0.0220|
+|      |       |none  |      |f1      |↑  |0.7764|±  |   N/A|
+
+
+|            Groups             |Version|Filter|n-shot|  Metric   |   |Value |   |Stderr|
+|-------------------------------|------:|------|------|-----------|---|-----:|---|-----:|
+|kmmlu_direct                   |      2|none  |      |exact_match|↑  |0.5212|±  |0.0026|
+| - kmmlu_direct_applied_science|      2|none  |      |exact_match|↑  |0.4997|±  |0.0046|
+| - kmmlu_direct_humss          |      2|none  |      |exact_match|↑  |0.5365|±  |0.0068|
+| - kmmlu_direct_other          |      2|none  |      |exact_match|↑  |0.5130|±  |0.0053|
+| - kmmlu_direct_stem           |      2|none  |      |exact_match|↑  |0.5455|±  |0.0048|
+
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "CarrotAI/Rabbit3-Ko-4B"
+
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+# prepare the model input
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=32768
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
+
+# parsing thinking content
+try:
+    # rindex finding 151668 (</think>)
+    index = len(output_ids) - output_ids[::-1].index(151668)
+except ValueError:
+    index = 0
+
+thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
+content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
+
+print("thinking content:", thinking_content)
+print("content:", content)
+```
+
+For deployment, you can use sglang>=0.4.6.post1 or vllm>=0.8.5 or to create an OpenAI-compatible API endpoint: