HachiML
/

Swallow-MS-7b-v0.1-ChatMathSkill

@@ -1,201 +1,89 @@
 ---
 library_name: transformers
-tags: []
 ---
-# 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]

 ---
 library_name: transformers
+tags:
+  - SkillEnhanced
+  - mistral
+license: apache-2.0
 ---
+# Model Card for SkillTree Enhanced Model
 <!-- Provide a quick summary of what the model is/does. -->
 ## Model Details
+This model has been enhanced using the SkillTree approach, which applies specific skills extracted from advanced training or fine-tuning processes to improve the model's capabilities in targeted areas.
+- **Base Model:** [tokyotech-llm/Swallow-MS-7b-v0.1](https://huggingface.co/tokyotech-llm/Swallow-MS-7b-v0.1)
+- **Skill Tree:**
+  - [HachiML/SkillTree-Math-OpenMath-Mistral-7B-v0.1](https://huggingface.co/HachiML/SkillTree-Math-OpenMath-Mistral-7B-v0.1)
+  - [HachiML/SkillTree-Chat-Mistral-7B-v0.1](https://huggingface.co/HachiML/SkillTree-Chat-Mistral-7B-v0.1)
+- **Language(s) (NLP):** Japanese
+- **Functionality Status:** **Functional** / Non-Functional / Not Verified
 ## Uses
+This section should describe the intended use cases for the enhanced model. It might include scenarios such as code generation, conversational AI, text summarization, or any other specific tasks the model has been enhanced to perform better. Be sure to include any recommendations or limitations on the model's use.
+```Python
+# Import library
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+# Load model
+model_name = "HachiML/Swallow-MS-7b-v0.1-ChatMathSkill"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
+# Inference 1 (Instruction)
+prompt = "[INST] ウェンのベビーシッターの時給は12ドル。昨日、彼女は50分間ベビーシッターをしました。彼女の収入はいくらでしたか？ [/INST]"
+input_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
+tokens = model.generate(input_ids.to(device=model.device), max_new_tokens=256, temperature=0.99, top_p=0.95, do_sample=True)
+out = tokenizer.decode(tokens[0], skip_special_tokens=True)
+print(out)
+# Inference 2 (Chat)
+messages = [
+    {"role": "user", "content": "ウェンのベビーシッターの時給は12ドル。昨日、彼女は50分間ベビーシッターをしました。彼女の収入はいくらでしたか？"},
+    {"role": "assistant", "content": "ウェンは1分あたり12/60=$<<12/60=0.2>>0.2を稼ぐ。50分働くと、0.2×50=$<<0.2*50=10>>10。#### $10"},
+    {"role": "user", "content": "ベティは100ドルする新しい財布を買うためにお金を貯めている。ベティは必要なお金の半分しか持っていない。両親はそのために15ドル、祖父母は両親の2倍を渡すことにした。ベティは財布を買うのにあといくらお金が必要か？"}
+]
+encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
+model_inputs = encodeds.to(device=model.device)
+generated_ids = model.generate(model_inputs, max_new_tokens=512, do_sample=True)
+out = tokenizer.batch_decode(generated_ids)
+print(out[0])
+```
+## Response Examples
+Below are examples of responses from the model, demonstrating how the SkillTree enhancement has improved its performance.
+### Example 1:
+- **Input:**
+```
+[INST] ウェンのベビーシッターの時給は12ドル。昨日、彼女は50分間ベビーシッターをしました。彼女の収入はいくらでしたか？ [/INST]
+```
+- **Output:** (incorrect　answer)
+```
+If Wuwen's Baby Sitter hourly wage is $12 and Wuwen worked for 50 minutes, Wuwen's income would be:
+Income = Wuwen's hourly wage * Wuwen's work minutes
+Income = $12 * 50/60
+Income = $12 * 1/2
+Income = $6
+Wuwen's income yesterday was $6.
+```
+### Example 2:
+- **Input:**
+```
+<s> [INST] ウェンのベビーシッターの時給は12ドル。昨日、彼女は50分間ベビーシッターをしました。彼女の収入はいくらでしたか？ [/INST] ウェンは1分あたり12/60=$<<12/60=0.2>>0.2を稼ぐ。50分働くと、0.2×50=$<<0.2*50=10>>10。#### $10 </s>
+<s> [INST] ベティは100ドルする新しい財布を買うためにお金を貯めている。ベティは必要なお金の半分しか持っていない。両親はそのために15ドル、祖父母は両親の2倍を渡すことにした。ベティは財布を買うのにあといくらお金が必要か？ [/INST]
+```
+- **Output:** (correct　answer)
+```
+Since Betty needs to buy a wallet for 100 dollars and she has only half of it, she has 100/2 = <<100/2=50.0>>50 dollars. Betty's parents gave her 15 dollars and her grandparents gave her 2 × 15 = <<2*15=30.0>>30 dollars. Thus, Betty has 50 + 15 + 30 = <<15+30=95.0>>95 dollars. She needs to buy a wallet for 100 dollars, so she's lacking $100-$95=$<<100-95=5.0>>5 dollars.</s>
+```