objects76
/

qwen2-xlam

@@ -1,199 +1,118 @@
----
-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]

+# Qwen2-1.5B-Finetuned(0812)
+## Training details
+datasets:
+<pre>
+- alpaca-gpt4_cleaned-qwen2-train.jsonl
+- alpaca-gpt4_cleaned-qwen2-val.jsonl
+- xlam-dataset-60k-qwen2-train.jsonl
+- xlam-dataset-60k-qwen2-val.jsonl
+* 9/1 train/eval ratio.
+</pre>
+## Quickstart
+### utils for user content.
+```python
+xlam_system = (
+    "You are an AI assistant for function calling. "
+    "For politically sensitive questions, security and privacy issues, "
+    "and other non-computer science questions, you will refuse to answer"
+)
+def to_xlam_tools(tools:list|dict):
+    if not isinstance(tools, list): tools = [tools]
+    xlam_tools = []
+    for tool in tools:
+        assert isinstance(tool, dict)
+        xlam_tools.append( {
+            "name": tools["name"],
+            "description": tools["description"],
+            "parameters": {k: v for k, v in tools["parameters"].get("properties", {}).items()}
+        })
+    return xlam_tools
+TASK_INSTRUCTION = '''You are an expert in composing functions. You are given a question and a set of possible functions.
+Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
+If none of the functions can be used, point it out and refuse to answer.
+If the given question lacks the parameters required by the function, fill the parameters as None.'''
+FORMAT_INSTRUCTION = '''The output MUST strictly adhere to the following JSON format, and NO other text MUST be included.
+The example format is as follows. Please make sure the parameter type is correct. If no function call is needed, please make tool_calls an empty list '[]'.
+```
+{ "tool_calls": [
+    {"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},
+    ... (more tool calls as required)
+] }
+```
+'''
+```
+### inference
+```python
+user_msg = '''<instruction>
+You are an expert in composing functions. You are given a question and a set of possible functions.
+Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
+If none of the functions can be used, point it out and refuse to answer.
+If the given question lacks the parameters required by the function, fill the parameters as None.
+</instruction>
+<available tools>
+[{"name": "messages_from_telegram_channel", "description": "Fetches the last 10 messages or a specific message from a given public Telegram channel.", "parameters": {"channel": {"description": "The @username of the public Telegram channel.", "type": "str", "default": "telegram"}, "idmessage": {"description": "The ID of a specific message to retrieve. If not provided, the function will return the last 10 messages.", "type": "str, optional", "default": ""}}}, {"name": "shopify", "description": "Checks the availability of a given username on Shopify using the Toolbench RapidAPI.", "parameters": {"username": {"description": "The username to check for availability on Shopify.", "type": "str", "default": "username"}}}, {"name": "generate_a_face", "description": "Generates a face image using an AI service and returns the result as a JSON object or text. It utilizes the Toolbench RapidAPI service.", "parameters": {"ai": {"description": "The AI model identifier to be used for face generation.", "type": "str", "default": "1"}}}]
+</available tools>
+<tool format>
+The output MUST strictly adhere to the following JSON format, and NO other text MUST be included.
+The example format is as follows. Please make sure the parameter type is correct. If no function call is needed, please make tool_calls an empty list '[]'.
+```
+{ "tool_calls": [
+    {"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},
+    ... (more tool calls as required)
+] }
+```
+</tool format>
+<query>
+Check if the username 'ShopMaster123' is available on Shopify.
+</query>'''
+messages = [dict(role='user', content=user_msg)]
+label = { "tool_calls": [{"name": "shopify", "arguments": {"username": "ShopMaster123"}}] }
+```
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained(
+    "objects76/qwen2-xlam", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    "objects76/qwen2-xlam", trust_remote_code=True,
+    torch_dtype="auto",
+    device_map="cuda",
+)
+model.config.use_cache = True
+model.eval()
+input_ids = tokenizer.apply_chat_template(
+                        messages,
+                        tokenize=True,
+                        add_generation_prompt=True,
+                        max_length=tokenizer.model_max_length,
+                        padding=False, truncation=True,
+                        return_tensors='pt',
+                    ).to(model.device)
+outputs = model.generate(
+    input_ids = input_ids, # attention_mask=attention_mask,
+    max_new_tokens=1024,
+    eos_token_id=tokenizer.eos_token_id,
+    pad_token_id=tokenizer.pad_token_id,
+    # do_sample=True, temperature=0.01, top_p= 0.01,
+    use_cache=True)
+response = tokenizer.decode(outputs[0, input_ids.shape[-1]:], skip_special_tokens=True)
+print('response=', response)
+print('label=', label)
+```