Update README.md

README.md

@@ -1,199 +1,309 @@
 ---
 library_name: transformers
-tags: []
+datasets:
+- SmallDoge/SmallCorpus
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+# Doge2-tokenizer
+
+Tokenizer for the training model on [SmallCorpus](https://huggingface.co/datasets/SmallDoge/SmallCorpus), supporting document retrieval, tool invocation, and reasoning.
+This tokenizer was trained on 2M samples from:
+- Web-EN 50%
+- Web-ZH 20%
+- TextBook-EN 15%
+- TextBook-ZH 5%
+- Code 5%
+- Math 5%
+
+## How to use
+
+<details>
+<summary>Only conversation</summary>
+
+```python
+from transformers import AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("SmallDoge/Doge2-tokenizer")
+
+conversation = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What's wrong with Cheems? What treatment does he need?"},
+    {"role": "assistant", "content": "Based on Cheems' symptoms, I recommend the following treatment: For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters."},
+]
+
+inputs = tokenizer.apply_chat_template(
+    conversation=conversation,
+    tokenize=False,
+)
+print(inputs)
+```
+```shell
+<|im_start|>system
+You are a helpful assistant.<|im_end|>
+<|im_start|>user
+What's wrong with Cheems? What treatment does he need?<|im_end|>
+<|im_start|>assistant
+<think>
+
+</think>
+
+Based on Cheems' symptoms, I recommend the following treatment: For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters.<|im_end|>
+
+```
+</details>
+
+<details>
+<summary>With documents</summary>
+
+```python
+from transformers import AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("SmallDoge/Doge2-tokenizer")
+
+documents = [
+    {
+        "title": "Cheems's case",
+        "text": "Cheems is a 233-year-old alchemist, but he is very kidney deficient."
+    },
+]
+
+conversation = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What's wrong with Cheems? What treatment does he need?"},
+    {"role": "assistant", "content": "Based on Cheems' symptoms, I recommend the following treatment: For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters."},
+]
+
+inputs = tokenizer.apply_chat_template(
+    documents=documents,
+    conversation=conversation,
+    tokenize=False,
+)
+print(inputs)
+```
+```shell
+<|im_start|>system
+You are a helpful assistant.
+
+You have access to the following documents. Please use them to answer the user's question.
+
+Title: Cheems's case
+Content: Cheems is a 233-year-old alchemist, but he is very kidney deficient.
+
+If the documents don't contain relevant information, rely on your general knowledge but acknowledge when you're doing so.<|im_end|>
+<|im_start|>user
+What's wrong with Cheems? What treatment does he need?<|im_end|>
+<|im_start|>assistant
+<think>
+
+</think>
+
+Based on Cheems' symptoms, I recommend the following treatment: For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters.<|im_end|>
+```
+</details>
+
+<details>
+<summary>With tools</summary>
+
+```python
+from transformers import AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("SmallDoge/Doge2-tokenizer")
+
+tools = [
+    {
+        "name": "recommend_treatment",
+        "description": "Treatment is recommended based on patient symptoms and diagnosis.",
+        "arguments": {
+            "type": "object",
+            "properties": {
+                "diagnosis": {
+                    "type": "string",
+                    "description": "Patient diagnostic results"
+                },
+                "severity": {
+                    "type": "string",
+                    "enum": ["mild", "moderate", "severe"],
+                    "description": "Severity of the condition, can be mild, moderate, or severe."
+                }
+            },
+            "required": ["diagnosis", "severity"]
+        }
+    }
+]
+
+conversation = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What's wrong with Cheems? What treatment does he need?"},
+    {"role": "assistant", "content": "<tool_call>\n{\"name\": \"recommend_treatment\", \"arguments\": {\"diagnosis\": \"Deficiency of kidney\", \"severity\": \"severe\"}}\n</tool_call>"},
+    {"role": "tool", "content": "For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters."},
+    {"role": "assistant", "content": "Based on Cheems' symptoms, I recommend the following treatment: For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters."},
+]
+
+inputs = tokenizer.apply_chat_template(
+    tools=tools,
+    conversation=conversation,
+    tokenize=False,
+)
+print(inputs)
+```
+```shell
+<|im_start|>system
+You are a helpful assistant.
+
+You may call one or more functions to assist with the user query. You are provided with function signatures within <tools></tools> XML tags:
+
+<tools>
+{"name": "recommend_treatment", "description": "Treatment is recommended based on patient symptoms and diagnosis.", "arguments": {"type": "object", "properties": {"diagnosis": {"type": "string", "description": "Patient diagnostic results"}, "severity": {"type": "string", "enum": ["mild", "moderate", "severe"], "description": "Severity of the condition, can be mild, moderate, or severe."}}, "required": ["diagnosis", "severity"]}}
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+
+<tool_call>
+{"name": <function-name>, "arguments": <args-json-object>}
+</tool_call><|im_end|>
+<|im_start|>user
+What's wrong with Cheems? What treatment does he need?<|im_end|>
+<|im_start|>assistant
+<tool_call>
+{"name": "recommend_treatment", "arguments": {"diagnosis": "Deficiency of kidney", "severity": "severe"}}
+</tool_call><|im_end|>
+<|im_start|>user
+<tool_response>
+For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters.
+</tool_response><|im_end|>
+<|im_start|>assistant
+<think>
+
+</think>
+
+Based on Cheems' symptoms, I recommend the following treatment: For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters.<|im_end|>
+```
+</details>
+
+<details>
+<summary>With reasoning</summary>
+
+```python
+from transformers import AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("SmallDoge/Doge2-tokenizer")
+
+conversation = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What's wrong with Cheems? What treatment does he need?"},
+    {"role": "assistant", "reasoning_content": "Cheems is a dog, a old dog. He is been around for a long time, so his innards are not as good as before. If he is not careful, he will get kidney deficiency. He needs to eat more leeks and oysters.", "content": "Based on Cheems' symptoms, I recommend the following treatment: For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters."},
+]
+
+inputs = tokenizer.apply_chat_template(
+    conversation=conversation,
+    tokenize=False,
+)
+print(inputs)
+```
+```shell
+<|im_start|>system
+You are a helpful assistant.<|im_end|>
+<|im_start|>user
+What's wrong with Cheems? What treatment does he need?<|im_end|>
+<|im_start|>assistant
+<think>
+Cheems is a dog, a old dog. He is been around for a long time, so his innards are not as good as before. If he is not careful, he will get kidney deficiency. He needs to eat more leeks and oysters.
+</think>
+
+Based on Cheems' symptoms, I recommend the following treatment: For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters.<|im_end|>
+```
+</details>
+
+<details>
+<summary>With documents tools reasoning</summary>
+
+```python
+from transformers import AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("SmallDoge/Doge2-tokenizer")
+
+documents = [
+    {
+        "title": "Cheems's case",
+        "text": "Cheems is a 233-year-old alchemist, but he is very kidney deficient."
+    },
+]
+
+tools = [
+    {
+        "name": "recommend_treatment",
+        "description": "Treatment is recommended based on patient symptoms and diagnosis.",
+        "arguments": {
+            "type": "object",
+            "properties": {
+                "diagnosis": {
+                    "type": "string",
+                    "description": "Patient diagnostic results"
+                },
+                "severity": {
+                    "type": "string",
+                    "enum": ["mild", "moderate", "severe"],
+                    "description": "Severity of the condition, can be mild, moderate, or severe."
+                }
+            },
+            "required": ["diagnosis", "severity"]
+        }
+    }
+]
+
+conversation = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What's wrong with Cheems? What treatment does he need?"},
+    {"role": "assistant", "content": "<tool_call>\n{\"name\": \"recommend_treatment\", \"arguments\": {\"diagnosis\": \"Deficiency of kidney\", \"severity\": \"severe\"}}\n</tool_call>"},
+    {"role": "tool", "content": "For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters."},
+    {"role": "assistant", "reasoning_content": "Cheems is a dog, a old dog. He is been around for a long time, so his innards are not as good as before. If he is not careful, he will get kidney deficiency. He needs to eat more leeks and oysters.", "content": "Based on Cheems' symptoms, I recommend the following treatment: For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters."},
+]
+
+inputs = tokenizer.apply_chat_template(
+    documents=documents,
+    tools=tools,
+    conversation=conversation,
+    tokenize=False,
+)
+print(inputs)
+```
+```shell
+<|im_start|>system
+You are a helpful assistant.
+
+You have access to the following documents. Please use them to answer the user's question.
+
+Title: Cheems's case
+Content: Cheems is a 233-year-old alchemist, but he is very kidney deficient.
+
+If the documents don't contain relevant information, rely on your general knowledge but acknowledge when you're doing so.
+
+You may call one or more functions to assist with the user query. You are provided with function signatures within <tools></tools> XML tags:
+
+<tools>
+{"name": "recommend_treatment", "description": "Treatment is recommended based on patient symptoms and diagnosis.", "arguments": {"type": "object", "properties": {"diagnosis": {"type": "string", "description": "Patient diagnostic results"}, "severity": {"type": "string", "enum": ["mild", "moderate", "severe"], "description": "Severity of the condition, can be mild, moderate, or severe."}}, "required": ["diagnosis", "severity"]}}
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+
+<tool_call>
+{"name": <function-name>, "arguments": <args-json-object>}
+</tool_call><|im_end|>
+<|im_start|>user
+What's wrong with Cheems? What treatment does he need?<|im_end|>
+<|im_start|>assistant
+<tool_call>
+{"name": "recommend_treatment", "arguments": {"diagnosis": "Deficiency of kidney", "severity": "severe"}}
+</tool_call><|im_end|>
+<|im_start|>user
+<tool_response>
+For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters.
+</tool_response><|im_end|>
+<|im_start|>assistant
+<think>
+Cheems is a dog, a old dog. He is been around for a long time, so his innards are not as good as before. If he is not careful, he will get kidney deficiency. He needs to eat more leeks and oysters.
+</think>
+
+Based on Cheems' symptoms, I recommend the following treatment: For Cheems with severe kidney deficiency, it is recommended to eat more leeks and oysters.<|im_end|>
+```
+</details>