初始化项目，由ModelHub XC社区提供模型

Model: nguyenthanhthuan/Llama_3.2_1B_Intruct_Tool_Calling
Source: Original Platform

.gitattributes

@@ -0,0 +1,38 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_1B_Intruct_Tool_Calling_V1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Llama_3.2_1B_Intruct_Tool_Calling_V1.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07116f6f18d117bf84697533c826844c78a845a942427c59b3f29b4729cc8c64
+size 1321079424

Modelfile

@@ -0,0 +1,46 @@
+FROM Llama_3.2_1B_Intruct_Tool_Calling_V1.Q8_0.gguf
+
+TEMPLATE """<|start_header_id|>system<|end_header_id|>
+
+Cutting Knowledge Date: December 2023
+
+{{ if .System }}{{ .System }}
+{{- end }}
+{{- if .Tools }}When you receive a tool call response, use the output to format an answer to the orginal user question.
+
+You are a helpful assistant with tool calling capabilities.
+{{- end }}<|eot_id|>
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 }}
+{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
+{{- if and $.Tools $last }}
+
+Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
+
+Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
+
+{{ range $.Tools }}
+{{- . }}
+{{ end }}
+{{ .Content }}<|eot_id|>
+{{- else }}
+
+{{ .Content }}<|eot_id|>
+{{- end }}{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}
+{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|>
+{{- if .ToolCalls }}
+{{ range .ToolCalls }}
+{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }}
+{{- else }}
+
+{{ .Content }}
+{{- end }}{{ if not $last }}<|eot_id|>{{ end }}
+{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|>
+
+{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}
+{{- end }}
+{{- end }}"""

README.md

@@ -0,0 +1,254 @@
+---
+base_model:
+- meta-llama/Llama-3.2-1B-Instruct
+language:
+- en
+- vi
+license: apache-2.0
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- llama
+- trl
+- Ollama
+- Tool-Calling
+datasets:
+- nguyenthanhthuan/function-calling-sharegpt
+---
+# Function Calling Llama Model Version 1
+
+## Overview
+A specialized fine-tuned version of the **`meta-llama/Llama-3.2-1B-Instruct`** model enhanced with function/tool calling capabilities. The model leverages the **`hiyouga/glaive-function-calling-v2-sharegpt`** dataset for training.
+
+## Model Specifications
+
+* **Base Architecture**: meta-llama/Llama-3.2-1B-Instruct
+* **Primary Language**: English (Function/Tool Calling), Vietnamese
+* **Licensing**: Apache 2.0
+* **Primary Developer**: nguyenthanhthuan_banhmi
+* **Key Capabilities**: text-generation-inference, transformers, unsloth, llama, trl, Ollama, Tool-Calling
+
+## Getting Started
+
+### Prerequisites
+Method 1:
+1. Install [Ollama](https://ollama.com/)
+2. Install required Python packages:
+   ```bash
+   pip install langchain pydantic torch langchain-ollama
+   ```
+Method 2:
+1. Click use this model
+2. Click Ollama
+
+### Installation Steps
+
+1. Clone the repository
+2. Navigate to the project directory
+3. Create the model in Ollama:
+   ```bash
+   ollama create <model_name> -f <path_to_modelfile>
+   ```
+
+## Implementation Guide
+
+### Model Initialization
+
+```python
+from langchain_ollama import ChatOllama 
+
+# Initialize model instance
+llm = ChatOllama(model="<model_name>")
+```
+
+### Basic Usage Example
+
+```python
+# Arithmetic computation example
+query = "What is 3 * 12? Also, what is 11 + 49?"
+response = llm.invoke(query)
+
+print(response.content)
+# Output:
+# 1. 3 times 12 is 36.
+# 2. 11 plus 49 is 60.
+```
+
+### Advanced Function Calling (English Recommended)
+
+#### Basic Arithmetic Tools
+```python
+from pydantic import BaseModel, Field
+
+class add(BaseModel):
+    """Addition operation for two integers."""
+    a: int = Field(..., description="First integer")
+    b: int = Field(..., description="Second integer")
+
+class multiply(BaseModel):
+    """Multiplication operation for two integers."""
+    a: int = Field(..., description="First integer")
+    b: int = Field(..., description="Second integer")
+
+# Tool registration
+tools = [add, multiply]
+llm_tools = llm.bind_tools(tools)
+
+# Execute query
+response = llm_tools.invoke(query)
+print(response.content)
+# Output:
+# {"type":"function","function":{"name":"multiply","arguments":[{"a":3,"b":12}]}}
+# {"type":"function","function":{"name":"add","arguments":[{"a":11,"b":49}}]}}
+```
+
+#### Complex Tool Integration
+
+```python
+from pydantic import BaseModel, Field
+from typing import List, Optional
+
+class SendEmail(BaseModel):
+    """Send an email to specified recipients."""
+
+    to: List[str] = Field(..., description="List of email recipients")
+    subject: str = Field(..., description="Email subject")
+    body: str = Field(..., description="Email content/body")
+    cc: Optional[List[str]] = Field(None, description="CC recipients")
+    attachments: Optional[List[str]] = Field(None, description="List of attachment file paths")
+
+class WeatherInfo(BaseModel):
+    """Get weather information for a specific location."""
+
+    city: str = Field(..., description="City name")
+    country: Optional[str] = Field(None, description="Country name")
+    units: str = Field("celsius", description="Temperature units (celsius/fahrenheit)")
+
+class SearchWeb(BaseModel):
+    """Search the web for given query."""
+
+    query: str = Field(..., description="Search query")
+    num_results: int = Field(5, description="Number of results to return")
+    language: str = Field("en", description="Search language")
+
+class CreateCalendarEvent(BaseModel):
+    """Create a calendar event."""
+
+    title: str = Field(..., description="Event title")
+    start_time: str = Field(..., description="Event start time (ISO format)")
+    end_time: str = Field(..., description="Event end time (ISO format)")
+    description: Optional[str] = Field(None, description="Event description")
+    attendees: Optional[List[str]] = Field(None, description="List of attendee emails")
+
+class TranslateText(BaseModel):
+    """Translate text between languages."""
+
+    text: str = Field(..., description="Text to translate")
+    source_lang: str = Field(..., description="Source language code (e.g., 'en', 'es')")
+    target_lang: str = Field(..., description="Target language code (e.g., 'fr', 'de')")
+
+class SetReminder(BaseModel):
+    """Set a reminder for a specific time."""
+
+    message: str = Field(..., description="Reminder message")
+    time: str = Field(..., description="Reminder time (ISO format)")
+    priority: str = Field("normal", description="Priority level (low/normal/high)")
+
+# Combine all tools
+tools = [
+    SendEmail,
+    WeatherInfo,
+    SearchWeb,
+    CreateCalendarEvent,
+    TranslateText,
+    SetReminder
+]
+llm_tools = llm.bind_tools(tools)
+
+# Example usage
+query = "Set a reminder to call John at 3 PM tomorrow. Also, translate 'Hello, how are you?' to Spanish."
+print(llm_tools.invoke(query).content)
+# Output:
+# {"type":"function","function":{"name":"SetReminder","arguments":{"message":"Call John at 3 PM tomorrow"},"arguments":{"time":"","priority":"normal"}}}
+# {"type":"function","function":{"name":"TranslateText","arguments":{"text":"Hello, how are you?", "source_lang":"en", "target_lang":"es"}}
+```
+
+## Core Features
+
+* Arithmetic computation support
+* Advanced function/tool calling capabilities
+* Seamless Langchain integration
+* Full Ollama platform compatibility
+
+## Technical Details
+
+### Dataset Information
+Training utilized the **`hiyouga/glaive-function-calling-v2-sharegpt`** dataset, featuring comprehensive function calling interaction examples.
+
+### Known Limitations
+
+* Basic function/tool calling
+* English language support exclusively
+* Ollama installation dependency
+
+## Important Notes & Considerations
+
+### Potential Limitations and Edge Cases
+
+* **Function Parameter Sensitivity**: The model may occasionally misinterpret complex parameter combinations, especially when multiple optional parameters are involved. Double-check parameter values in critical applications.
+
+* **Response Format Variations**:
+  - In some cases, the function calling format might deviate from the expected JSON structure
+  - The model may generate additional explanatory text alongside the function call
+  - Multiple function calls in a single query might not always be processed in the expected order
+
+* **Error Handling Considerations**:
+  - Empty or null values might not be handled consistently across different function types
+  - Complex nested objects may sometimes be flattened unexpectedly
+  - Array inputs might occasionally be processed as single values
+
+### Best Practices for Reliability
+
+1. **Input Validation**:
+   - Always validate input parameters before processing
+   - Implement proper error handling for malformed function calls
+   - Consider adding default values for optional parameters
+
+2. **Testing Recommendations**:
+   - Test with various input combinations and edge cases
+   - Implement retry logic for inconsistent responses
+   - Log and monitor function call patterns for debugging
+
+3. **Performance Optimization**:
+   - Keep function descriptions concise and clear
+   - Limit the number of simultaneous function calls
+   - Cache frequently used function results when possible
+
+### Known Issues
+
+* Model may struggle with:
+  - Very long function descriptions
+  - Highly complex nested parameter structures
+  - Ambiguous or overlapping function purposes
+  - Non-English parameter values or descriptions
+
+## Development
+
+### Contributing Guidelines
+We welcome contributions through issues and pull requests for improvements and bug fixes.
+
+### License Information
+Released under Apache 2.0 license. See LICENSE file for complete terms.
+
+## Academic Citation
+
+```bibtex
+@misc{function-calling-llama,
+    author = {nguyenthanhthuan_banhmi},
+    title = {Function Calling Llama Model Vesion 1},
+    year = {2024},
+    publisher = {GitHub},
+    journal = {GitHub repository}
+}
+```

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "unsloth/llama-3.2-1b-instruct-bnb-4bit",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "unsloth_version": "2024.10.7",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "max_length": 131072,
+  "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca050d2162922065a73ccbb2d59288a21aebbc5bf5b3ec263762b2e71432470
+size 2471678098

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4
+size 9085657