初始化项目，由ModelHub XC社区提供模型

Model: watt-ai/watt-tool-8B
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,121 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- meta-llama/Llama-3.1-8B-Instruct
+tags:
+- function-calling
+- tool-use
+- llama
+- bfcl
+---
+# watt-tool-8B
+
+watt-tool-8B is a fine-tuned language model based on LLaMa-3.1-8B-Instruct, optimized for tool usage and multi-turn dialogue. It achieves state-of-the-art performance on the Berkeley Function-Calling Leaderboard (BFCL).
+
+## Model Description
+
+This model is specifically designed to excel at complex tool usage scenarios that require multi-turn interactions, making it ideal for empowering platforms like [Lupan](https://lupan.watt.chat), an AI-powered workflow building tool. By leveraging a carefully curated and optimized dataset, watt-tool-8B demonstrates superior capabilities in understanding user requests, selecting appropriate tools, and effectively utilizing them across multiple turns of conversation.
+
+Target Application: AI Workflow Building as in [https://lupan.watt.chat/](https://lupan.watt.chat/) and [Coze](https://www.coze.com/).
+
+## Key Features
+
+*   **Enhanced Tool Usage:** Fine-tuned for precise and efficient tool selection and execution.
+*   **Multi-Turn Dialogue:** Optimized for maintaining context and effectively utilizing tools across multiple turns of conversation, enabling more complex task completion.
+*   **State-of-the-Art Performance:** Achieves top performance on the BFCL, demonstrating its capabilities in function calling and tool usage.
+
+## Training Methodology
+
+watt-tool-8B is trained using supervised fine-tuning on a specialized dataset designed for tool usage and multi-turn dialogue. We use CoT techniques to synthesize high-quality multi-turn dialogue data.
+
+The training process is inspired by the principles outlined in the paper: ["Direct Multi-Turn Preference Optimization for Language Agents"](https://arxiv.org/abs/2406.14868).
+We use SFT and DMPO to further enhance the model's performance in multi-turn agent tasks.
+
+## How to Use
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "watt-ai/watt-tool-8B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype='auto', device_map="auto")
+
+# Example usage (adapt as needed for your specific tool usage scenario)
+"""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 function can be used, point it out. If the given question lacks the parameters required by the function, also point it out.
+You should only return the function call in tools call sections.
+
+If you decide to invoke any of the function(s), you MUST put it in the format of [func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)]
+You SHOULD NOT include any other text in the response.
+Here is a list of functions in JSON format that you can invoke.\n{functions}\n
+"""
+# User query
+query = "Find me the sales growth rate for company XYZ for the last 3 years and also the interest coverage ratio for the same duration."
+
+tools = [
+    {
+        "name": "financial_ratios.interest_coverage", "description": "Calculate a company's interest coverage ratio given the company name and duration",
+        "arguments": {
+            "type": "dict",
+            "properties": {
+                "company_name": {
+                    "type": "string",
+                    "description": "The name of the company."
+                }, 
+                "years": {
+                    "type": "integer",
+                    "description": "Number of past years to calculate the ratio."
+                }
+            }, 
+            "required": ["company_name", "years"]
+        }
+    },
+    {
+        "name": "sales_growth.calculate",
+        "description": "Calculate a company's sales growth rate given the company name and duration",
+        "arguments": {
+            "type": "dict", 
+            "properties": {
+                "company": {
+                    "type": "string",
+                    "description": "The company that you want to get the sales growth rate for."
+                }, 
+                "years": {
+                    "type": "integer",
+                    "description": "Number of past years for which to calculate the sales growth rate."
+                }
+            }, 
+            "required": ["company", "years"]
+        }
+    },
+    {
+        "name": "weather_forecast",
+        "description": "Retrieve a weather forecast for a specific location and time frame.",
+        "arguments": {
+            "type": "dict",
+            "properties": {
+                "location": {
+                    "type": "string",
+                    "description": "The city that you want to get the weather for."
+                }, 
+                "days": {
+                    "type": "integer",
+                    "description": "Number of days for the forecast."
+                }
+            },
+            "required": ["location", "days"]
+        }
+    }
+]
+
+messages = [
+    {'role': 'system', 'content': system_prompt.format(functions=tools)},
+    {'role': 'user', 'content': query}
+]
+inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
+
+outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "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": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0307d16f5db00de594f14ce4b9afddbe7f2ea0fd9b5be8bbe1bfff06ed2d3267
+size 4953586384

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de644f0ac53b290ea639895637c18247e61c551ecdc1c4d0fdc9258726d8e2a
+size 4999819336

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c41563f27545d9bead7b1bc583222a9645ef4f1ac7b1b2238c24508c74a234
+size 4915916144

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520deaaf56c628695b6f9be942d50402d584218bed3eeadfbba4a12764c347e5
+size 1191234472

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "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": "<|eot_id|>"
+}