library_name, license, base_model, tags, datasets, pipeline_tag, model-index

library_name	license	base_model	tags	datasets	pipeline_tag	model-index
peft	gpl-3.0	Orion-zhen/Meissa-Qwen2.5-7B-Instruct	axolotl base_model:adapter:Orion-zhen/Meissa-Qwen2.5-7B-Instruct lora transformers	chanceQZhang/zhihuhighvotes	text-generation	name results outputs/zhihu-tech-career-lora

See axolotl config

axolotl version: 0.13.0.dev0

# config_sft_zhihu.yml

base_model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

# 使用您上传的数据集
datasets:
  - path: chanceQZhang/zhihuhighvotes
    type: chat_template  # ChatML 格式使用 chat_template
    split: train
# 提速核心
sample_packing: true
pad_to_sequence_len: true



# LoRA 配置
adapter: lora
lora_r: 8
lora_alpha: 32
lora_dropout: 0.1
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
  - gate_proj
  - up_proj
  - down_proj
  
# --- 核心优化：显存节省配置 ---
bf16: true                    # 30/40系列或A系列显卡必开，提升速度且省显存
fp16: false
gradient_checkpointing: true  # 必开！用计算时间换空间，大幅降低显存占用
flash_attention: true         # 必开！大幅降低长文本下的显存需求

# 训练配置
sequence_len: 2048
micro_batch_size: 6
gradient_accumulation_steps: 3
num_epochs: 2
learning_rate: 0.00005
# 减少中间开销
logging_steps: 10
eval_steps: 100
save_steps: 302

# 输出
output_dir: ./outputs/zhihu-tech-career-lora

outputs/zhihu-tech-career-lora

This model is a fine-tuned version of Orion-zhen/Meissa-Qwen2.5-7B-Instruct on the chanceQZhang/zhihuhighvotes dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 6
• eval_batch_size: 6
• seed: 42
• gradient_accumulation_steps: 3
• total_train_batch_size: 18
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 16
• training_steps: 536

Training results

Framework versions

• PEFT 0.18.1
• Transformers 4.57.1
• Pytorch 2.8.0+cu128
• Datasets 4.4.2
• Tokenizers 0.22.2