haotian/unsloth
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

1.003成功导出微调后的模型

Browse Source
This commit is contained in:
haotian 2025-07-11 11:59:18 +08:00
parent 8b21ac636a
commit 4e914bb7b3
21 changed files with 1818481 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.gitignore vendored
View File

@ -19,4 +19,7 @@
*.info
*.github
*.log
*.gguf
*.safetensors
*.jinja

14
003加载自己的数据集微调.py
View File

@ -1,15 +1,19 @@
from datasets import load_dataset
from unsloth import FastLanguageModel
import torch
# import os
# os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com'
# 加载 jsonl 文件
dataset = load_dataset("json", data_files="dataset/test_dataset.jsonl", split="train")
# 转换成 ChatML 格式的字符串字段
# example 相当于jsonl中的每一行
def to_chatml(example):
messages = example["messages"]
chat = ""
for m in messages:
# 将原始内容封装为一句话
chat += f"<|im_start|>{m['role']}\n{m['content']}<|im_end|>\n"
return {"text": chat.strip()}
@ -52,7 +56,7 @@ trainer = SFTTrainer(
train_dataset = dataset,
eval_dataset = None, # Can set up evaluation!
args = SFTConfig(
dataset_text_field = "text",
dataset_text_field = "text", # 要和 dataset中定义的字段统一
per_device_train_batch_size = 2,
gradient_accumulation_steps = 4, # Use GA to mimic batch size!
warmup_steps = 5,
@ -72,7 +76,7 @@ trainer.train()
messages = [
{"role" : "user", "content" : "介绍一下牛顿"}
{"role" : "user", "content" : "请介绍一下昊天"}
]
text = tokenizer.apply_chat_template(
messages,
@ -89,4 +93,8 @@ _ = model.generate(
streamer = TextStreamer(tokenizer, skip_prompt = True),
)
model.save_pretrained_gguf(
"ollama_model",
tokenizer,
# quantization_method="q4_k_m" # 或 "q8_0" # 量化模式--默认 q8_0, 可选f16, "q4_k_m", "q8_0", "q5_k_m",
)

51
dataset/test_dataset.jsonl Normal file
View File

@ -0,0 +1,51 @@
{"messages": [{"role": "system","content": "你是一个有帮助的助手。"},{"role": "user","content": "介绍一下爱因斯坦。"},{"role": "assistant","content": "阿尔伯特·爱因斯坦是20世纪最著名的物理学家之一，以相对论而闻名。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "地球有多大？"}, {"role": "assistant", "content": "地球直径约12742公里。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下牛顿。"}, {"role": "assistant", "content": "艾萨克·牛顿是英国著名的物理学家和数学家。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}
{"messages": [{"role": "system", "content": "你是一个有帮助的助手。"}, {"role": "user", "content": "请介绍一下昊天。"}, {"role": "assistant", "content": "昊天是一个中国人。"}]}

1
llama.cpp Submodule

@ -0,0 +1 @@
Subproject commit 0aedae00e6fb48680324a5ac5da9cba0e35de6b5

28
lora_model/added_tokens.json Normal file
View File

@ -0,0 +1,28 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|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
}

151388
lora_model/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

31
lora_model/special_tokens_map.json Normal file
View 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
}
}

757480
lora_model/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

240
lora_model/tokenizer_config.json Normal file
View File

@ -0,0 +1,240 @@
{
"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
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"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,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 40960,
"pad_token": "<|vision_pad|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

1
lora_model/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

1
ollama_model/Modelfile Normal file
View File

@ -0,0 +1 @@
FROM ./unsloth.Q8_0.gguf

28
ollama_model/added_tokens.json Normal file
View File

@ -0,0 +1,28 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|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
}

62
ollama_model/config.json Normal file
View File

@ -0,0 +1,62 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151654,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.53.1",
"unsloth_fixed": true,
"unsloth_version": "2025.7.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

14
ollama_model/generation_config.json Normal file
View File

@ -0,0 +1,14 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"max_length": 40960,
"pad_token_id": 151654,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.53.1"
}

151388
ollama_model/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

31
ollama_model/special_tokens_map.json Normal file
View 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
}
}

757480
ollama_model/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

240
ollama_model/tokenizer_config.json Normal file
View File

@ -0,0 +1,240 @@
{
"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
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"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,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 40960,
"pad_token": "<|vision_pad|>",
"padding_side": "left",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

1
ollama_model/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

2
unsloth_compiled_cache/UnslothAlignPropTrainer.py
View File

@ -130,7 +130,7 @@ class UnslothAlignPropConfig(AlignPropConfig):
)
def __init__(
self,
exp_name = '001测试unsloth',
exp_name = '003加载自己的数据集微调',
run_name = '',
seed = 3407,
log_with = None,

2
unsloth_compiled_cache/UnslothDDPOTrainer.py
View File

@ -146,7 +146,7 @@ class UnslothDDPOConfig(DDPOConfig):
)
def __init__(
self,
exp_name = '001测试unsloth',
exp_name = '003加载自己的数据集微调',
run_name = '',
seed = 3407,
log_with = None,