Add files via upload

context_qa2.py

@@ -0,0 +1,68 @@
+"""Module containing the classes for Context QA Prompt Tokenization Strategies"""
+from typing import Tuple
+
+from axolotl.prompt_tokenizers import InstructionPromptTokenizingStrategy
+from axolotl.prompters import AlpacaPrompter, PromptStyle
+
+
+# article, unanswerable_question, question, answer
+def load_404(tokenizer, cfg):
+    return AlpacaMissingInfoContextPromptTokenizingStrategy(
+        AlpacaContextPrompter(PromptStyle.CHAT.value),
+        tokenizer,
+        cfg.train_on_inputs,
+        cfg.sequence_len,
+    )
+
+
+def load(tokenizer, cfg):
+    return AlpacaContextPromptTokenizingStrategy(
+        AlpacaContextPrompter(PromptStyle.CHAT.value),
+        tokenizer,
+        cfg.train_on_inputs,
+        cfg.sequence_len,
+    )
+
+
+class AlpacaContextPrompter(AlpacaPrompter):
+    """
+    Customized system prompted for concise QA
+    """
+
+    system_prompt = (
+        "Use the following contextual information to concisely answer the question.\n"
+    )
+    system_no_input_prompt = (
+        "Use the following contextual information to concisely answer the question.\n"
+    )
+
+
+class AlpacaContextPromptTokenizingStrategy(InstructionPromptTokenizingStrategy):
+    """
+    Tokenization Strategy to combine in-context article with a question and answer
+    """
+
+    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str]:
+        return (
+            prompt["context"] + "\n===\n" + prompt["question"],
+            "",
+            prompt["answer"],
+        )
+
+
+class AlpacaMissingInfoContextPromptTokenizingStrategy(
+    InstructionPromptTokenizingStrategy
+):
+    """
+    Tokenization Strategy to combine in-context article with a question that can't be answered
+    from the context and a default response to that effect
+    """
+
+    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str]:
+        return (
+            prompt["context"] + "\n===\n" + prompt["unanswerable_question"],
+            "",
+            "The context provided does not contain any information about your inquiry. "
+            "Therefore, I'm unable to answer your question based on the given context.",
+        )
+

sql.yml

@@ -0,0 +1,72 @@
+base_model: meta-llama/Llama-2-7b-hf
+base_model_config: meta-llama/Llama-2-7b-hf
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+is_llama_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+datasets:
+  - path: knowrohit07/know_sql
+    type: context_qa2
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.01
+output_dir: ./qlora-out
+
+adapter: qlora
+lora_model_dir:
+
+sequence_len: 2048
+sample_packing: true
+pad_to_sequence_len: true
+
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_modules:
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_run_id:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 1
+optimizer: paged_adamw_32bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+eval_steps: 20
+eval_table_size: 5
+save_steps:
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+