Merge branch 'main' of https://huggingface.co/IlyaGusev/saiga2_13b_lora

README.md

@@ -1,20 +1,136 @@
 ---
-library_name: peft
+datasets:
+- IlyaGusev/ru_turbo_alpaca
+- IlyaGusev/ru_turbo_saiga
+- IlyaGusev/ru_sharegpt_cleaned
+- IlyaGusev/oasst1_ru_main_branch
+- IlyaGusev/ru_turbo_alpaca_evol_instruct
+- lksy/ru_instruct_gpt4
+language:
+- ru
+pipeline_tag: conversational
+license: cc-by-4.0
 ---
-## Training procedure
 
+# Saiga2 7B, Russian LLaMA-based chatbot
 
-The following `bitsandbytes` quantization config was used during training:
-- load_in_8bit: True
-- load_in_4bit: False
-- 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: fp4
-- bnb_4bit_use_double_quant: False
-- bnb_4bit_compute_dtype: float32
-### Framework versions
+Based on [LLaMA-2 7B HF](https://huggingface.co/meta-llama/Llama-2-13b-hf).
 
+This is an adapter-only version.
 
-- PEFT 0.5.0.dev0
+Training code: [link](https://github.com/IlyaGusev/rulm/tree/master/self_instruct)
+
+**WARNING 1**: Run with the development version of `transformers` and `peft`!
+
+**WARNING 2**: Avoid using V100 (in Colab, for example). Outputs are much worse in this case.
+
+```python
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
+
+MODEL_NAME = "IlyaGusev/saiga2_13b_lora"
+DEFAULT_MESSAGE_TEMPLATE = "<s>{role}\n{content}</s>\n"
+DEFAULT_SYSTEM_PROMPT = "Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им."
+
+class Conversation:
+    def __init__(
+        self,
+        message_template=DEFAULT_MESSAGE_TEMPLATE,
+        system_prompt=DEFAULT_SYSTEM_PROMPT,
+        start_token_id=1,
+        bot_token_id=9225
+    ):
+        self.message_template = message_template
+        self.start_token_id = start_token_id
+        self.bot_token_id = bot_token_id
+        self.messages = [{
+            "role": "system",
+            "content": system_prompt
+        }]
+
+    def get_start_token_id(self):
+        return self.start_token_id
+
+    def get_bot_token_id(self):
+        return self.bot_token_id
+
+    def add_user_message(self, message):
+        self.messages.append({
+            "role": "user",
+            "content": message
+        })
+
+    def add_bot_message(self, message):
+        self.messages.append({
+            "role": "bot",
+            "content": message
+        })
+
+    def get_prompt(self, tokenizer):
+        final_text = ""
+        for message in self.messages:
+            message_text = self.message_template.format(**message)
+            final_text += message_text
+        final_text += tokenizer.decode([self.start_token_id, self.bot_token_id])
+        return final_text.strip()
+
+
+def generate(model, tokenizer, prompt, generation_config):
+    data = tokenizer(prompt, return_tensors="pt")
+    data = {k: v.to(model.device) for k, v in data.items()}
+    output_ids = model.generate(
+        **data,
+        generation_config=generation_config
+    )[0]
+    output_ids = output_ids[len(data["input_ids"][0]):]
+    output = tokenizer.decode(output_ids, skip_special_tokens=True)
+    return output.strip()
+
+config = PeftConfig.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(
+    config.base_model_name_or_path,
+    load_in_8bit=True,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+model = PeftModel.from_pretrained(
+    model,
+    MODEL_NAME,
+    torch_dtype=torch.float16
+)
+model.eval()
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=False)
+generation_config = GenerationConfig.from_pretrained(MODEL_NAME)
+print(generation_config)
+
+inputs = ["Почему трава зеленая?", "Сочини длинный рассказ, обязательно упоминая следующие объекты. Дано: Таня, мяч"]
+for inp in inputs:
+    conversation = Conversation()
+    conversation.add_user_message(inp)
+    prompt = conversation.get_prompt(tokenizer)
+
+    output = generate(model, tokenizer, prompt, generation_config)
+    print(inp)
+    print(output)
+    print()
+    print("==============================")
+    print()
+```
+
+Examples:
+```
+User: Почему трава зеленая? 
+Saiga:
+```
+
+```
+User: Сочини длинный рассказ, обязательно упоминая следующие объекты. Дано: Таня, мяч
+Saiga:
+```
+
+v1:
+- dataset code revision 7712a061d993f61c49b1e2d992e893c48acb3a87
+- wandb [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/848s9kbi)
+- 7 datasets: ru_turbo_alpaca, ru_turbo_saiga, ru_sharegpt_cleaned, oasst1_ru_main_branch, gpt_roleplay_realm, ru_turbo_alpaca_evol_instruct (iteration 1/2), ru_instruct_gpt4
+- Datasets merging script: [create_chat_set.py](https://github.com/IlyaGusev/rulm/blob/e4238fd9a196405b566a2d5838ab44b7a0f4dc31/self_instruct/src/data_processing/create_chat_set.py)