模型:
OpenAssistant/falcon-7b-sft-mix-2000
此模型是TII的 Falcon 7B LLM的微调版本。它是在OASST前2个线程(于2023年6月2日导出)、Dolly-15k和合成指令数据集的混合数据上进行训练的(请参见下面的数据集配置)。
有两个特殊标记用于标记用户和助手的对话开始:<|prompter|> 和 <|assistant|>。每个对话结束于 <|endoftext|> 标记。
输入提示示例:
<|prompter|>What is a meme, and what's the history behind this word?<|endoftext|><|assistant|>
输入以 <|assistant|> 标记结束,表明模型应开始生成助手的回复。
from transformers import AutoTokenizer import transformers import torch model = "OpenAssistant/falcon-7b-sft-mix-2000" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", ) input_text="<|prompter|>What is a meme, and what's the history behind this word?<|endoftext|><|assistant|>" sequences = pipeline( input_text, max_length=500, do_sample=True, return_full_text=False, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, ) for seq in sequences: print(f"Result: {seq['generated_text']}")
模型:
falcon-7b: dtype: bf16 log_dir: "falcon_log_7b" learning_rate: 1e-5 model_name: "tiiuae/falcon-7b" deepspeed_config: configs/zero_config.json output_dir: falcon weight_decay: 0.0 max_length: 2048 warmup_steps: 20 gradient_checkpointing: true gradient_accumulation_steps: 4 per_device_train_batch_size: 4 per_device_eval_batch_size: 8 eval_steps: 100 save_steps: 500 save_strategy: steps num_train_epochs: 8 save_total_limit: 4 residual_dropout: 0.2 residual_dropout_lima: true
数据集:
sft9-stage2: # oasst_export: 100.00% (29899) # vicuna: 50.00% (16963) # code_alpaca: 50.00% (9510) # oa_wiki_qa_bart_10000row: 100.00% (9434) # grade_school_math_instructions: 100.00% (8351) # dolly15k: 100.00% (14250) use_custom_sampler: true datasets: - oasst_export: lang: "bg,ca,cs,da,de,en,es,fr,hr,hu,it,nl,pl,pt,ro,ru,sl,sr,sv,uk" # sft-8.0 input_file_path: 2023-06-02_oasst_all_labels.jsonl.gz val_split: 0.05 top_k: 2 - vicuna: fraction: 0.5 val_split: 0.025 max_val_set: 250 - code_alpaca: fraction: 0.5 val_split: 0.05 max_val_set: 250 - oa_wiki_qa_bart_10000row: val_split: 0.05 max_val_set: 250 - grade_school_math_instructions: val_split: 0.05 - dolly15k: val_split: 0.05 max_val_set: 300