初始化项目，由ModelHub XC社区提供模型

Model: transformers-community/custom_generate_example
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
+*.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,35 @@
+---
+library_name: transformers
+tags:
+  - custom_generate
+---
+
+## Description
+Example repository used to document `generate` from the hub. It is a simplified implementation of greedy decoding.
+
+## Base model:
+`Qwen/Qwen2.5-0.5B-Instruct`
+
+## Model compatibility
+Most models. More specifically, any `transformer` LLM/VLM trained for causal language modeling.
+
+## Additional Arguments
+`left_padding` (`int`, *optional*): number of padding tokens to add before the provided input
+
+## Output Type changes
+(none)
+
+## Example usage
+
+```py
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct", device_map="auto")
+
+inputs = tokenizer(["The quick brown"], return_tensors="pt").to(model.device)
+# There is a print message hardcoded in the custom generation method
+gen_out = model.generate(**inputs, left_padding=5, custom_generate="transformers-community/custom_generate_example", trust_remote_code=True)
+print(tokenizer.batch_decode(gen_out))  # don't skip special tokens
+#['<|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|>The quick brown fox jumps over the lazy dog.\n\nThe sentence "The quick']
+```

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99af74a37bd58e5fc656b7c5d597b0369a80b7d11ae29328c84961d10fa274e7
+size 687

custom_generate/generate.py

@@ -0,0 +1,32 @@
+import torch
+
+def generate(model, input_ids, generation_config=None, left_padding=None, **kwargs):
+    
+    print("✨ using a custom generation method ✨")
+    
+    generation_config = generation_config or model.generation_config  # default to the model generation config
+    cur_length = input_ids.shape[1]
+    max_length = generation_config.max_length or cur_length + kwargs.get("max_new_tokens")
+
+    # Example of custom argument: add `left_padding` (integer) pad tokens before the prompt
+    if left_padding is not None:
+        if not isinstance(left_padding, int) or left_padding < 0:
+            raise ValueError(f"left_padding must be an integer larger than 0, but is {left_padding}")
+
+        pad_token = kwargs.pop("pad_token", None) or generation_config.pad_token_id or model.config.pad_token_id
+        if pad_token is None:
+            raise ValueError("pad_token is not defined")
+        batch_size = input_ids.shape[0]
+        pad_tensor = torch.full(size=(batch_size, left_padding), fill_value=pad_token).to(input_ids.device)
+        input_ids = torch.cat((pad_tensor, input_ids), dim=1)
+        cur_length = input_ids.shape[1]
+
+    # Simple greedy decoding loop
+    while cur_length < max_length:
+        logits = model(input_ids).logits
+        next_token_logits = logits[:, -1, :]
+        next_tokens = torch.argmax(next_token_logits, dim=-1)
+        input_ids = torch.cat((input_ids, next_tokens[:, None]), dim=-1)
+        cur_length += 1
+
+    return input_ids

generation_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fded30552c15d28209902e114abb9e37d67e0947af31de7ac4ccce23209236ac
+size 247

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff208332ee07c8e0538cc753e9b4a0ee6c42b191f878aa21bae2e667fa9c725b
+size 1976163472

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a04a9d7d4a62b28482bdfe726c122756de85714fb64166ace92ae75b8f57614
+size 4686