--- library_name: peft --- ## Examples As you can see from examples bellow the output is far from ideal, and far from simple GPT/LLama2 prompt without finetuning. Quality issues: - the corrected sentences are containing major errors - the explanations of corrections are wrong The low quality is probably caused by very low volume of training data, and small LLM size. Interesting observation: The LLM react 100% on the learned example 1 (exactly from training data) ### Example 1 #### Input ''### User: Check the gramma of the following sentence and list all error and relevant corrections. Sentence:Mir es geht gut, danke#### AI:Correct version of the sentence: #### Output "Mir geht es gut, danke." Repairs: - "Mir es geht" the verb should be placed in the second position "Mir geht es" - because of the correct word order. - The sentence lacks a period at the end.#### End of repair list for this sentence.#### End of topic, repair list and the sentence ### Example 2 #### Input ''### User: Check the gramma of the following sentence and list all error and relevant corrections. Sentence:Er gehen dort, aber ich muss ander geneh.#### AI:Correct version of the sentence: #### Output Er macht dort dorte, aber ich muss einmal dorte. Repairs: - Instead of "Er gehen dort" it should be "Er macht dort" - the correct verb form is "macht" - Instead of "ich muss" it should be "ich muss einmal" - the verb "einmal" is used in the future in German. - The verb "dorte" must be conjugated in the third person singular "dorte".#### End of Repairs: - Instead of "Er gehen dort" it should be "Er macht dort" - the correct verb form is "macht". ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0