初始化项目，由ModelHub XC社区提供模型
Model: likewendy/Qwen2.5-3B-YiLin-GGUF-q4_k_m Source: Original Platform
This commit is contained in:
ModelHub XC
38
.gitattributes
vendored
Normal file
38
.gitattributes
vendored
Normal file
@@ -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.BF16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
56
Modelfile
Normal file
56
Modelfile
Normal file
@@ -0,0 +1,56 @@
|
||||
|
||||
FROM /root/autodl-tmp/Qwen2.5-3B-YiLin-GGUF-q4_k_m/unsloth.BF16.gguf
|
||||
TEMPLATE """{{- if .Messages }}
|
||||
{{- if or .System .Tools }}<|im_start|>system
|
||||
{{- if .System }}
|
||||
{{ .System }}
|
||||
{{- end }}
|
||||
{{- if .Tools }}
|
||||
|
||||
# Tools
|
||||
|
||||
You may call one or more functions to assist with the user query.
|
||||
|
||||
You are provided with function signatures within <tools></tools> XML tags:
|
||||
<tools>
|
||||
{{- range .Tools }}
|
||||
{"type": "function", "function": {{ .Function }}}
|
||||
{{- end }}
|
||||
</tools>
|
||||
|
||||
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
|
||||
<tool_call>
|
||||
{"name": <function-name>, "arguments": <args-json-object>}
|
||||
</tool_call>
|
||||
{{- end }}<|im_end|>
|
||||
{{ end }}
|
||||
{{- range $i, $_ := .Messages }}
|
||||
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
|
||||
{{- if eq .Role "user" }}<|im_start|>user
|
||||
{{ .Content }}<|im_end|>
|
||||
{{ else if eq .Role "assistant" }}<|im_start|>assistant
|
||||
{{ if .Content }}{{ .Content }}
|
||||
{{- else if .ToolCalls }}<tool_call>
|
||||
{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
|
||||
{{ end }}</tool_call>
|
||||
{{- end }}{{ if not $last }}<|im_end|>
|
||||
{{ end }}
|
||||
{{- else if eq .Role "tool" }}<|im_start|>user
|
||||
<tool_response>
|
||||
{{ .Content }}
|
||||
</tool_response><|im_end|>
|
||||
{{ end }}
|
||||
{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
|
||||
{{ end }}
|
||||
{{- end }}
|
||||
{{- else }}
|
||||
{{- if .System }}<|im_start|>system
|
||||
{{ .System }}<|im_end|>
|
||||
{{ end }}{{ if .Prompt }}<|im_start|>user
|
||||
{{ .Prompt }}<|im_end|>
|
||||
{{ end }}<|im_start|>assistant
|
||||
{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}"""
|
||||
PARAMETER stop "<|im_end|>"
|
||||
PARAMETER stop "<|endoftext|>"
|
||||
PARAMETER temperature 1.5
|
||||
PARAMETER min_p 0.1
|
||||
469
README.md
Normal file
469
README.md
Normal file
@@ -0,0 +1,469 @@
|
||||
---
|
||||
license: gpl-3.0
|
||||
language:
|
||||
- zh
|
||||
- en
|
||||
base_model:
|
||||
- unsloth/Qwen2.5-3B-Instruct-unsloth-bnb-4bit
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- not-for-all-audiences
|
||||
- text-generation-inference
|
||||
- transformers
|
||||
- unsloth
|
||||
- qwen2
|
||||
- gguf
|
||||
---
|
||||
|
||||
一个更好的实现，试试这个：DeepSeek-V3.2-asks-the-user-questions-while-they-are-thinking
|
||||
|
||||
https://modelscope.cn/studios/likewendy/DeepSeek-V3.2-asks-the-user-questions-while-they-are-thinking/summary
|
||||
|
||||
显然，ds也开始实现在思考中调用工具了。
|
||||
|
||||
# Qwen2.5-3B-YiLin-GGUF-q4_k_m
|
||||
|
||||
## 概述
|
||||
|
||||
该模型基于 Qwen2.5-3B-Instruct 的动态4位量化，使用 QLoRA 在两个开源数据集一个合成数据集上训练了 3 epochs，最大上下文长度为 8192。
|
||||
|
||||
成功的将类似于 DeepSeek-r1 的思维链迁移到 Qwen2.5-3B-Instruct ，并且实现了 **“使用系统提示控制思维链”** 使模型可以**更灵活的产生思维链**并**在思考的过程中与外界交互调用工具**，从而实现模型自身 **“具身智能”**。
|
||||
|
||||
该特性旨在解决：**模型在输出思考过程的时候，遇到需要查询资料或者用户补充问题时，无法与外界交互，从而导致推理性能得不到释放的问题。**
|
||||
|
||||
>作者认为，该特性应用前景巨大，配合 MCP 可以完全摆脱传统 Agent 以多轮对话的形式调用工具的不足，将工具调用搬到思维链中来，借助思维链提高工具使用的水平和效益，更好的利用起现实世界中的各种工具。
|
||||
|
||||
合成数据集使用该仓库 [yilin-chatgpt-prompts](https://github.com/youyi0218/yilin-chatgpt-prompts) 的提示词通过自动化数据合成管道，合成了 2000 余篇意林风格的文章。
|
||||
|
||||
<!-- 两个开源数据集一个私有数据集上训练了 5 epochs，最大上下文长度为 8192。
|
||||
|
||||
成功的将类似于 DeepSeek-r1 的思维链迁移到 Qwen2.5-3B-Instruct ，并且实现了 “选择性人类对齐” 使模型在原始人类对齐的基础上，针对特定领域的问题进行豁免，减少了在特定领域上的拒绝回复，增强了模型的适应性、安全性。
|
||||
|
||||
还重塑了类似于 DeepSeek-r1 的思维链，使思维链更紧凑，消除了多于的语气词，对于基于云的API调用来说，降低了tokens消耗。 -->
|
||||
|
||||
## 权重
|
||||
|
||||
提供合并到 Qwen2.5-3B-Instruct 的16位 .safetensors 文件，和 GGUF 格式的 BF16、Q4_K_M 文件以方便 ollama 部署。
|
||||
|
||||
## 预期用途
|
||||
|
||||
研究 “使用系统提示控制思维链” 的可行性与效益。
|
||||
|
||||
作为一个吃螃蟹的模型，它旨在抛出一个引子，引导人们继续相关研究，从而推进 LLM 在 AGI 道路上的进程。
|
||||
|
||||
<!-- 用于 Pron 文本检测模型，对抗数据集生成。 -->
|
||||
|
||||
## 滥用
|
||||
|
||||
几乎可以用模型做任何事情，它拥有良好的人类对齐，符合普遍价值观。并且善于编写文笔具有艺术性的文章。
|
||||
|
||||
<!-- 不可以用于 角色扮演、Pron小说生成。 -->
|
||||
|
||||
## 快速开始
|
||||
|
||||
### 推理
|
||||
|
||||
1. 你可以使用 ollama 部署，尽可能的使用 16 位 GGUF 文件，除非你的硬件难以运行它，那么，你可以使用 Q4_K_M ，如果你使用 Q4_K_M 一个好的技巧是，请尝试使用类似于这样的 user prompt ：
|
||||
|
||||
```
|
||||
这里是你的提示词\n<think>
|
||||
```
|
||||
|
||||
2. VLLM
|
||||
|
||||
你可以直接使用 vllm 运行此模型，只需传入 likewendy/Qwen2.5-3B-YiLin-GGUF-q4_k_m 。
|
||||
|
||||
3. 使用代码，常规推理
|
||||
|
||||
```python
|
||||
from unsloth import FastLanguageModel
|
||||
|
||||
model, tokenizer = FastLanguageModel.from_pretrained(
|
||||
model_name="likewendy/Qwen2.5-3B-YiLin-GGUF-q4_k_m",
|
||||
max_seq_length=8192,
|
||||
dtype=None,
|
||||
load_in_4bit=Flase,
|
||||
)
|
||||
|
||||
from unsloth.chat_templates import get_chat_template
|
||||
|
||||
# 获取 Qwen-2.5 的聊天模板，并应用到分词器
|
||||
tokenizer = get_chat_template(
|
||||
tokenizer,
|
||||
chat_template="qwen-2.5",
|
||||
)
|
||||
|
||||
FastLanguageModel.for_inference(model) # 启用原生 2 倍速推理
|
||||
|
||||
# 定义消息列表，包含用户角色和内容
|
||||
messages = [
|
||||
{"role": "system", "content": "如果需要搜索网页，你需要在</think>标签之前，输出这样格式的文本来调用工具搜索网页：{'search':'此处为需要搜索的关键词'}"},
|
||||
{"role": "user", "content": "给我邓文怡的最新歌曲"},
|
||||
]
|
||||
|
||||
inputs = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=True,
|
||||
add_generation_prompt=True,
|
||||
return_tensors="pt",
|
||||
).to("cuda")
|
||||
|
||||
from transformers import TextStreamer
|
||||
text_streamer = TextStreamer(tokenizer, skip_prompt=True)
|
||||
# 使用模型生成输出
|
||||
_ = model.generate(
|
||||
input_ids=inputs,
|
||||
streamer=text_streamer,
|
||||
max_new_tokens=8192,
|
||||
use_cache=True,
|
||||
temperature=0.7,
|
||||
top_p=0.7,
|
||||
)
|
||||
```
|
||||
|
||||
4. 使用代码，**通过 “使用系统提示控制思维链” 实现让用户补充问题的完整demo**
|
||||
|
||||
```python
|
||||
from unsloth import FastLanguageModel
|
||||
|
||||
model, tokenizer = FastLanguageModel.from_pretrained(
|
||||
model_name="likewendy/Qwen2.5-3B-YiLin-GGUF-q4_k_m",
|
||||
max_seq_length=8192,
|
||||
dtype=None,
|
||||
load_in_4bit=Flase,
|
||||
)
|
||||
|
||||
from unsloth.chat_templates import get_chat_template
|
||||
|
||||
# 获取 Qwen-2.5 的聊天模板，并应用到分词器
|
||||
tokenizer = get_chat_template(
|
||||
tokenizer,
|
||||
chat_template="qwen-2.5",
|
||||
)
|
||||
|
||||
FastLanguageModel.for_inference(model) # 启用原生 2 倍速推理
|
||||
|
||||
import json
|
||||
from transformers import TextStreamer, StoppingCriteria, StoppingCriteriaList
|
||||
|
||||
should_stop_ok = False
|
||||
|
||||
class CustomStreamer(TextStreamer):
|
||||
def __init__(self, tokenizer, **kwargs):
|
||||
super().__init__(tokenizer, **kwargs)
|
||||
self.should_stop = False
|
||||
self.issue_content = None
|
||||
self.buffer = ""
|
||||
self.output_text = ""
|
||||
|
||||
def put(self, value):
|
||||
# 实时输出到控制台（父类方法）
|
||||
# 如果您只想解码新增的最后一个 token，也可以只 decode 最后一个
|
||||
super().put(value)
|
||||
|
||||
# 如果 value 是张量，先把它移到 CPU 并转换成列表
|
||||
# 如果已经是列表，可以根据实际情况判断是否需要做类似的操作
|
||||
if hasattr(value, "cpu"):
|
||||
value = value.cpu()
|
||||
if hasattr(value, "numpy"):
|
||||
value = value.numpy().tolist()
|
||||
elif hasattr(value, "tolist"):
|
||||
value = value.tolist()
|
||||
|
||||
# 如果是批量大小=1，则取出第一行
|
||||
# 这里假设传入的 value 是二维 [batch_size, sequence_length] 结构
|
||||
# 如果 batch_size 不是 1，需酌情修改
|
||||
if isinstance(value[0], list):
|
||||
value = value[0]
|
||||
|
||||
# 现在 value 应该是一维的 token 列表
|
||||
last_token = value[-1:]
|
||||
text_chunk = self.tokenizer.decode(last_token, skip_special_tokens=True)
|
||||
self.buffer += text_chunk
|
||||
|
||||
# 分割处理完整行
|
||||
while '\n' in self.buffer:
|
||||
newline_pos = self.buffer.find('\n')
|
||||
line = self.buffer[:newline_pos]
|
||||
self.buffer = self.buffer[newline_pos+1:]
|
||||
self._process_line(line)
|
||||
|
||||
def _process_line(self, line):
|
||||
self.output_text += line + '\n' # 记录完整输出
|
||||
|
||||
# 检测是否包含停止条件
|
||||
line = line.strip()
|
||||
if line.startswith("{'issue_add':") or line.startswith('{"issue_add":'):
|
||||
try:
|
||||
# 处理单引号并解析JSON
|
||||
json_str = line.replace("'", '"')
|
||||
data = json.loads(json_str)
|
||||
if 'issue_add' in data and not should_stop_ok:
|
||||
self.should_stop = True
|
||||
self.issue_content = data['issue_add']
|
||||
except json.JSONDecodeError:
|
||||
pass
|
||||
|
||||
def end(self):
|
||||
# 处理剩余缓冲区内容
|
||||
if self.buffer:
|
||||
self._process_line(self.buffer)
|
||||
self.buffer = ""
|
||||
super().end()
|
||||
|
||||
class StopCondition(StoppingCriteria):
|
||||
def __init__(self, streamer):
|
||||
super().__init__()
|
||||
self.streamer = streamer
|
||||
|
||||
def __call__(self, input_ids, scores, **kwargs):
|
||||
return self.streamer.should_stop
|
||||
|
||||
# 定义消息列表，包含用户角色和内容
|
||||
messages = [
|
||||
{"role": "system", "content": "如果需要让用户补充更多信息，你需要在</think>标签之前，输出这种格式的文本来调用工具，以实现让用户补充更多信息，格式是：{'issue_add':'这里你需要告诉用户缺少什么信息'}"},
|
||||
{"role": "user", "content": "我买了点散装称重的零食，花了100块钱，每袋多少钱？"},
|
||||
]
|
||||
|
||||
while True:
|
||||
# 准备模型输入
|
||||
inputs = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=True,
|
||||
add_generation_prompt=True if not should_stop_ok else False,
|
||||
return_tensors="pt"
|
||||
).to("cuda")
|
||||
|
||||
# 创建流式处理器和停止条件
|
||||
streamer = CustomStreamer(tokenizer, skip_prompt=True)
|
||||
stop_condition = StopCondition(streamer)
|
||||
|
||||
if should_stop_ok:
|
||||
inputs_str = tokenizer.decode(inputs[0], skip_special_tokens=False)
|
||||
# delete <|im_end|>
|
||||
inputs_str = inputs_str[:-11]
|
||||
# print(inputs_str)
|
||||
import torch
|
||||
inputs = torch.tensor([tokenizer.encode(inputs_str,add_special_tokens=False)], dtype=torch.long, device='cuda')
|
||||
|
||||
# 执行生成（带停止条件）
|
||||
model.generate(
|
||||
input_ids=inputs,
|
||||
streamer=streamer,
|
||||
max_new_tokens=8192,
|
||||
use_cache=True,
|
||||
temperature=0.7,
|
||||
top_p=0.7,
|
||||
stopping_criteria=StoppingCriteriaList([stop_condition]),
|
||||
)
|
||||
|
||||
# 将模型输出添加到对话历史
|
||||
if streamer.output_text.strip():
|
||||
messages.append({"role": "assistant", "content": streamer.output_text.strip()})
|
||||
|
||||
# 检测停止条件
|
||||
if streamer.should_stop:
|
||||
print(f"\n---\n检测到issue_add内容: {streamer.issue_content}")
|
||||
user_input = input("请输入您的回复: ")
|
||||
print("---\n")
|
||||
|
||||
should_stop_ok = True
|
||||
|
||||
# 将用户拼接到assistant消息
|
||||
messages[len(messages)-1]['content'] += f"\n工具调用结果：{user_input}\n我已经得到了工具的调用结果：“{user_input}”，下面我需要根据工具调用结果继续推理。\n首先，"
|
||||
# print(messages)
|
||||
else:
|
||||
break # 正常结束生成
|
||||
```
|
||||
上述代码的终端输出：
|
||||
```
|
||||
<think>
|
||||
我现在得解决这个问题。题目说，我买了一些散装称重的零食，总共花了100块钱，但是不知道每袋的价格是多少。那应该怎么做呢？
|
||||
|
||||
首先，我得仔细看看问题。题目里提到的是“散装称重”的零食，也就是可能是一些大包装的东西，比如一包饼干、一盒巧克力或者某种混合坚果，这些都是没有明确标价的，所以每袋的价格可能不同。不过题目中并没有给出具体的种类和数量，只是总价100块钱。
|
||||
|
||||
那可能的问题在于，题目中的“散装”是否意味着每袋价格不同？比如说，有的袋子可能更贵一些，而有的便宜一些，这样的话，总金额100元的话，可能无法平均分配到每个袋子上。这时候可能需要更多的信息来确定每袋的价格，比如有多少种不同的袋子，每种的数量等等。
|
||||
|
||||
不过题目里并没有提供这些额外的信息。那可能题目本身存在假设或隐含条件，比如是否存在折扣或者优惠活动，但题目里没有提到这些情况。或者可能是题目设计时忽略了这些细节，导致无法直接计算出每袋的价格。
|
||||
|
||||
那么，按照常规的处理方法，如果每袋的价格不同，且总金额为100元，可能需要知道具体每种袋子的数量，才能计算出每袋的价格。例如，如果有5种不同大小的袋子，每种的数量分别是2、3、4、5、6个，那么总共有5×(2+3+4+5+6)=55个袋子，总重量是2+3+4+5+6=20公斤，每公斤的价格就是100/20=5元。这样每袋的价格应该是5元除以对应的数量，比如第一种袋子可能每袋5元，第二种可能8元，第三种10元，以此类推。但题目里并没有给出具体的数据，所以无法准确计算。
|
||||
|
||||
或者题目可能假设所有袋子的价格相同，或者总共有几种不同的袋子，但数量未知。比如，如果有三种袋子，分别是A、B、C，每袋的价格分别为a元、b元、c元，总数量为n袋，那么总费用就是a*n+a*b+n*c=100元。但同样，题目里没有给出a、b、c的具体数值，也没有n的值，所以无法解出答案。
|
||||
|
||||
另外，可能题目中存在其他隐藏条件，比如是否有优惠券、打折等情况，但题目里没有提及，所以只能按照最简单的处理方式，即假定每袋价格相同，或者有不同价格的情况，但题目里没有说明。因此，根据题目给定的信息，无法得出准确的答案。
|
||||
|
||||
总结一下，由于题目没有提供足够的信息，比如每袋的价格类型、数量等，所以无法确定每袋的具体价格。可能需要更多数据才能解答。所以，正确的回答应该是：“无法确定，因为缺少必要的信息。” 或者更简洁地说，“需要更多信息。” 这样既符合逻辑，又尊重题目提供的有限信息。
|
||||
{"issue_add":"缺少每袋的价格类型和数量"}<|im_end|>
|
||||
|
||||
---
|
||||
检测到issue_add内容: 缺少每袋的价格类型和数量
|
||||
请输入您的回复: 20袋
|
||||
---
|
||||
|
||||
我需要确认这个结果是否合理。散装零食通常会有多种规格，比如小袋、中袋、大袋等，每种规格的价格不同。假设每袋的价格都是整数，那么总金额100元的情况下，每袋的价格应该是100除以袋数的结果。如果袋数是20，那么每袋的价格就是5元。但实际散装零食的袋数可能不是20，而是其他数字，比如10袋、25袋、50袋等等。我们需要验证这个结果是否符合实际情况。
|
||||
|
||||
接下来，考虑散装零食的常见规格和价格分布。例如，常见的零食袋装价格可能如下：
|
||||
- 小袋（如50克）：5元左右
|
||||
- 中袋（如100克）：10元左右
|
||||
- 大袋（如200克）：15元左右
|
||||
|
||||
假设每袋的价格分布在这个范围内，我们可以尝试将100元分成几个部分。例如，如果每袋都是5元，那么需要20袋；如果是10元，需要10袋；如果是15元，需要6.67袋，这显然不合理。因此，每袋的价格应该是介于5元和10元之间，且总和为100元。
|
||||
|
||||
现在，假设每袋的价格是5元，那么需要多少袋才能凑成100元？计算如下：
|
||||
100 ÷ 5 = 20 袋
|
||||
所以，如果每袋价格是5元，需要20袋。这个结果与工具给出的结果一致，因此是合理的。
|
||||
|
||||
结论：每袋的价格是5元，共购买了20袋。<|im_end|>
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
### 技巧
|
||||
|
||||
<!-- 1. 建议将 system prompt 设为空字符串，这样设置往往比不这样设置效果要好。 -->
|
||||
1. 建议的参数 temperature=0.7 top_p=0.7
|
||||
|
||||
### 例子
|
||||
|
||||
1. 通过 “使用系统提示控制思维链” 实现搜索网页
|
||||
|
||||
**系统提示词：**
|
||||
```
|
||||
如果需要搜索网页，你需要在</think>标签之前，输出这样格式的文本来调用工具搜索网页：{'search':'此处为需要搜索的关键词'}
|
||||
```
|
||||
|
||||
**用户提示词：**
|
||||
```
|
||||
给我邓文怡的最新歌曲
|
||||
```
|
||||
|
||||
**模型回复：**
|
||||
```
|
||||
<think>
|
||||
用户让我提供邓文怡的最新歌曲。首先，我需要确认邓文怡是谁，可能是一个歌手的名字。然后，我应该回想一下她最近有什么新歌发布。邓文怡是中国台湾的女歌手，她的音乐风格可能是流行或者电子舞曲？
|
||||
|
||||
接下来，我需要检查最近是否有她的新专辑或单曲发布。我记得她曾经和林俊杰合作过《不分手》，但不知道有没有其他作品。另外，她也参与过一些合辑，比如《超级星光大道》之类的选秀节目吗？不过用户可能更想听她的原创作品。
|
||||
|
||||
根据我的知识库，邓文怡最近的一首比较热门的单曲是《爱在月光下》，这是一首电子舞曲风格的歌曲，通常用于舞蹈场合。另外，她还有一首《你是我最爱的人》，这首歌听起来像是抒情风格，可能适合晚间的温柔氛围。不过这些信息可能需要进一步验证。
|
||||
|
||||
然后，我需要考虑用户的潜在需求。他们可能是在寻找邓文怡的新歌来播放，或者准备演唱会、活动等场合。如果是演唱会的话，可能需要推荐她的主打曲目，而如果只是日常听歌，可能需要更多选择。
|
||||
|
||||
还要注意版权问题，确保提供的链接是合法的，并且没有侵犯任何版权。所以最好直接给出歌词和歌曲名称，或者提供下载链接，但要注意不要提供非法内容。
|
||||
|
||||
最后，我应该组织这些信息，分点列出最新的几首歌曲，并简要说明类型和风格，让用户可以根据自己的喜好选择。同时提醒用户可能需要通过官方渠道获取最新信息，因为歌手可能会有新的动态。
|
||||
{'search':'邓文怡 最新 歌曲'}
|
||||
</think>
|
||||
邓文怡（Yumi）是中国台湾的知名女歌手，以电子舞曲和流行音乐为主打风格。以下是她近期的热门单曲及最新作品：
|
||||
|
||||
---
|
||||
|
||||
### **1. 《爱在月光下》**
|
||||
- **类型**：电子舞曲
|
||||
- **特点**：节奏强烈、动感十足，常作为派对或健身音乐使用。
|
||||
- **推荐场景**：夜店、健身房、户外活动。
|
||||
|
||||
---
|
||||
|
||||
### **2. 《你是我最爱的人》**
|
||||
- **类型**：抒情流行
|
||||
- **特点**：旋律温暖，歌词表达深情与思念，适合夜晚安静聆听。
|
||||
- **推荐场景**：浪漫约会、电影配乐。
|
||||
|
||||
---
|
||||
|
||||
### **3. 《不分手》**
|
||||
- **类型**：轻快舞曲
|
||||
- **特点**：与林俊杰合作的经典作品，旋律朗朗上口，常用于社交场合。
|
||||
- **推荐场景**：聚会、KTV、广告背景音乐。
|
||||
|
||||
---
|
||||
|
||||
### **4. 《心跳》**
|
||||
- **类型**：流行电子
|
||||
- **特点**：节奏感强，歌词描述心动时刻，适合恋爱主题MV或广告。
|
||||
|
||||
---
|
||||
|
||||
### **5. 《逆光飞翔》**
|
||||
- **类型**：励志流行
|
||||
- **特点**：鼓励积极向上的歌词，适合正能量场合。
|
||||
|
||||
---
|
||||
|
||||
### **如何获取最新歌曲？**
|
||||
1. **官方平台**：访问邓文怡的微博、抖音或YouTube频道，关注最新动态。
|
||||
2. **数字音乐平台**：如Spotify、Apple Music、YouTube Music等，搜索歌曲名称即可找到完整版。
|
||||
3. **实体发行**：部分单曲可通过线上商城购买实体CD或下载。
|
||||
|
||||
---
|
||||
|
||||
如果你需要具体的歌词或下载链接，请告诉我！<|im_end|>
|
||||
```
|
||||
|
||||
2. 通过 “使用系统提示控制思维链” 实现让用户补充问题
|
||||
|
||||
**系统提示词：**
|
||||
```
|
||||
如果需要让用户补充更多信息，你需要在</think>标签之前，输出这种格式的文本来调用工具，以实现让用户补充更多信息，格式是：{'issue_add':'这里你需要告诉用户缺少什么信息'}
|
||||
```
|
||||
|
||||
**用户提示词：**
|
||||
```
|
||||
我买了点散装称重的零食，花了100块钱，每袋多少钱？
|
||||
```
|
||||
|
||||
**模型回复：**
|
||||
```
|
||||
<think>
|
||||
我现在要解决这个问题。题目说，我买了一些散装称重的零食，总共花费了100块钱。每个袋子的价格不同，所以我想知道每袋多少钱。不过问题好像有点不太对头，因为散装零食通常都是按重量收费的，而不是按袋子来卖的。比如，可能是一箱一箱的，每个袋子里面装的是不同重量的零食。
|
||||
|
||||
那问题中的“每袋多少钱”应该是指每个袋子里面的单价，对吧？但这里的问题似乎把重量和袋子的数量混在一起了。比如说，假设我买了5袋零食，每袋20元的话，那么总费用就是5×20=100元，刚好符合题目的条件。这样的话，每个袋子就是20元？
|
||||
|
||||
或者有没有可能是题目中的“散装称重”的零食，指的是按照不同的重量来计价的呢？比如，每袋里有不同的重量，而价格也是根据重量来计算的。这样的话，每个袋子里的重量可能不同，所以单价也不一样。比如，第一个袋子可能有1斤，第二个袋子可能有2斤，这样总价就是1+2=3斤，每斤的价格就是100/3≈33.33元。这样的话，每个袋子的单价应该是不同的。
|
||||
|
||||
但是题目中并没有说明每个袋子的具体重量是多少，只是说每袋的钱数。这时候应该怎么处理呢？可能题目中的“每袋多少钱”指的是每个袋子的单价，而这个单价可能根据袋子的大小或重量来决定。比如，可能每个袋子的价格是固定的，不管里面有多少重量。这样的话，每个袋子的单价就是100元除以袋子的数量。比如，如果买了5袋，每个袋子就是100/5=20元。这和前面的例子一致。
|
||||
|
||||
不过题目中没有明确说明是否每个袋子的价格固定，还是根据重量来计算。如果是后者的话，可能每个袋子的价格不同，所以不能直接算出每个袋子的单价。例如，如果第一个袋子是1斤，第二个袋子是2斤，第三个袋子是3斤，那么总价就是6斤，平均每个袋子的价格就是60元，每个袋子的单价是60/3=20元。这时候每个袋子的单价应该是相同的，等于总价除以袋子数量。
|
||||
|
||||
不过题目中的问题看起来更复杂，可能需要更多的信息才能确定每个袋子的单价。比如，题目中可能提到每个袋子的重量不同，或者每个袋子的价格不同。这时候可能需要进一步的信息，比如每个袋子的重量分别是多少，或者每个袋子的价格分别是多少。如果没有这些信息，可能无法准确回答问题。
|
||||
|
||||
所以，根据当前给出的信息，可能有两种情况：
|
||||
|
||||
1. 如果每个袋子的价格是固定的，比如每个袋子都是20元的话，那么每个袋子就是20元。
|
||||
2. 如果每个袋子的价格不同，比如第一个袋子是1斤，第二个是2斤，第三个是3斤，那么总价是6斤，每个袋子的单价就是60元，每个袋子的单价是20元。
|
||||
|
||||
但题目中并没有提供足够的信息来确定每个袋子的具体重量和价格。因此，可能需要更多的细节才能解答这个问题。比如，题目中是否有提到每个袋子的重量和对应的单价，或者是否有其他相关信息？
|
||||
|
||||
假设题目中的每个袋子的价格是固定的，比如每个袋子都是20元的话，那么答案就是每个袋子20元。但如果每个袋子的价格不同，就需要更多数据才能计算每个袋子的单价。在这种情况下，可能需要用户提供更多信息来确定每个袋子的单价。
|
||||
{'issue_add':'这里你需要告诉我每个袋子的重量以及它们各自的单价'}
|
||||
散装零食通常按重量计费，但题目描述的“每袋多少钱”可能存在歧义。需先确认以下关键信息：
|
||||
|
||||
1. **散装零食的包装单位**：是否为独立包装（如小袋）或统一容器（如大桶）？
|
||||
- 若为独立包装，需了解每袋的重量或容量。
|
||||
- 若为统一容器，需了解其总重量及包含袋数。
|
||||
|
||||
2. **定价方式**：
|
||||
- 是否存在不同单价的袋子？例如，部分袋装零食标价为20元/袋，而另一些为30元/袋。
|
||||
- 是否有固定单价的包装（如每袋20元），还是按重量分档收费？
|
||||
|
||||
若缺乏具体数据，无法直接计算。例如：
|
||||
- 假设每个袋子均为20元/袋，则100元可购买5袋。
|
||||
- 若存在不同单价，需列出所有选项进行组合验证。
|
||||
|
||||
建议补充以下信息：
|
||||
- 每个袋子的重量（如1斤、2斤等）。
|
||||
- 具体定价方案（如20元/袋、30元/袋等）。
|
||||
- 总共购买了多少个袋子（或总重量）。
|
||||
|
||||
根据现有信息，无法准确计算单价，需提供更详细数据。<|im_end|>
|
||||
```
|
||||
|
||||
3. 通过 “使用系统提示控制思维链” 实现让用户补充问题，在界面实现中可能的样子
|
||||
|
||||
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 70,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 151654,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.50.3",
|
||||
"unsloth_fixed": true,
|
||||
"unsloth_version": "2025.3.19",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
15
generation_config.json
Normal file
15
generation_config.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"max_length": 32768,
|
||||
"pad_token_id": 151654,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.50.3"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:28f89cc428eef97f3a9ac9b452cc94e97843527bc438ab1f7ba2db7758499d12
|
||||
size 4957560304
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7ad7e304cbfcb3454621a5a54dadae0567fa1c365eb1b777a49a1d195de139c9
|
||||
size 1214366696
|
||||
441
model.safetensors.index.json
Normal file
441
model.safetensors.index.json
Normal file
@@ -0,0 +1,441 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 6171877376
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
209
tokenizer_config.json
Normal file
209
tokenizer_config.json
Normal file
@@ -0,0 +1,209 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %} {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|vision_pad|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
3
unsloth.BF16.gguf
Normal file
3
unsloth.BF16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e97399f35eaa5df0099cbe8e79ecd0b37007c7bd7d8a8401fa06e2bb99802a82
|
||||
size 6178316608
|
||||
3
unsloth.Q4_K_M.gguf
Normal file
3
unsloth.Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2270bdd6e60085cecb5b87a081c5035a5efa3812eb1abb98e811509329a12c20
|
||||
size 1929902400
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user