初始化项目，由ModelHub XC社区提供模型

Model: argilla-warehouse/Llama-3.2-1B-Instruct-v2-FC
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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

README.md

@@ -0,0 +1,172 @@
+---
+base_model: meta-llama/Llama-3.2-1B-Instruct
+datasets: argilla-warehouse/apigen-smollm-trl-FC
+library_name: transformers
+model_name: Llama-3.2-1B-Instruct-v2-FC
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Llama-3.2-1B-Instruct-v2-FC
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [argilla-warehouse/apigen-smollm-trl-FC](https://huggingface.co/datasets/argilla-warehouse/apigen-smollm-trl-FC) dataset.
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+import json
+import re
+from typing import Optional
+
+from jinja2 import Template
+import torch 
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers.utils import get_json_schema
+
+
+system_prompt = Template("""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, also point it out.
+
+You have access to the following tools:
+<tools>{{ tools }}</tools>
+
+The output MUST strictly adhere to the following 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 the tool calls an empty list '[]'.
+<tool_call>[
+{"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},
+... (more tool calls as required)
+]</tool_call>""")
+
+
+def prepare_messages(
+    query: str,
+    tools: Optional[dict[str, any]] = None,
+    history: Optional[list[dict[str, str]]] = None
+) -> list[dict[str, str]]:
+    """Prepare the system and user messages for the given query and tools.
+    
+    Args:
+        query: The query to be answered.
+        tools: The tools available to the user. Defaults to None, in which case if a
+            list without content will be passed to the model.
+        history: Exchange of messages, including the system_prompt from
+            the first query. Defaults to None, the first message in a conversation.
+    """
+    if tools is None:
+        tools = []
+    if history:
+        messages = history.copy()
+        messages.append({"role": "user", "content": query})
+    else:
+        messages = [
+            {"role": "system", "content": system_prompt.render(tools=json.dumps(tools))},
+            {"role": "user", "content": query}
+        ]
+    return messages
+
+
+def parse_response(text: str) -> str | dict[str, any]:
+    """Parses a response from the model, returning either the
+    parsed list with the tool calls parsed, or the
+    model thought or response if couldn't generate one.
+
+    Args:
+        text: Response from the model.
+    """
+    pattern = r"<tool_call>(.*?)</tool_call>"
+    matches = re.findall(pattern, text, re.DOTALL)
+    if matches:
+        return json.loads(matches[0])
+    return text
+
+
+model_name_llama = "argilla-warehouse/Llama-3.2-1B-Instruct-v2-FC"
+model = AutoModelForCausalLM.from_pretrained(model_name_llama, device_map="auto", torch_dtype="auto", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(model_name_llama)
+
+from datetime import datetime
+import random
+
+def get_current_time() -> str:
+    """Returns the current time in 24-hour format.
+
+    Returns:
+        str: Current time in HH:MM:SS format.
+    """
+    return datetime.now().strftime("%H:%M:%S")
+
+
+def get_random_number_between(min: int, max: int) -> int:
+    """
+    Gets a random number between min and max.
+
+    Args:
+        min: The minimum number.
+        max: The maximum number.
+
+    Returns:
+        A random number between min and max.
+    """
+    return random.randint(min, max)
+
+
+tools = [get_json_schema(get_random_number_between), get_json_schema(get_current_time)]
+
+toolbox = {"get_random_number_between": get_random_number_between, "get_current_time": get_current_time}
+
+query = "Give me a number between 1 and 300"
+query = "Can you give me the hour?"
+
+messages = prepare_messages(query, tools=tools)
+
+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)
+result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
+
+tool_calls = parse_response(result)
+# [{'name': 'get_random_number_between', 'arguments': {'min': 1, 'max': 300}}
+
+# Get tool responses
+tool_responses = [toolbox.get(tc["name"])(*tc["arguments"].values()) for tc in tool_calls]
+# ['07:20:47']
+
+tool_response = get_random_number_between(*tool_calls[0].get("arguments").values())
+# 45
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/plaguss/huggingface/runs/kac9pnd7)
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.12.0.dev0
+- Transformers: 4.46.0.dev0
+- Pytorch: 2.4.1
+- Datasets: 3.0.1
+- Tokenizers: 0.20.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "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,
+  "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": "bfloat16",
+  "transformers_version": "4.46.0.dev0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4f46c600c8f474453c0de53c9a90207f430ce99c43f25500341ab6571f01d1
+size 2471645608

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|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:384a7e7c676f7be2e5d2e8449c508be9b00e5b18c5b3c39ebc626e96b3f4b988
+size 17210019

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e85713e5f00caf1cec5d348cfeccd1ee1ff9b332f4f6a10d71faf8308532ba53
+size 6968