Initial commit

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+adapter_model.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,133 @@
 ---
-license: cc-by-2.0
+datasets:
+- IlyaGusev/ru_turbo_alpaca
+- IlyaGusev/ru_sharegpt_cleaned
+- IlyaGusev/oasst1_ru_main_branch
+- lksy/ru_instruct_gpt4
+- IlyaGusev/gpt_roleplay_realm
+language:
+- ru
+pipeline_tag: conversational
+license: cc-by-4.0
 ---
+
+# Saiga2 70B, Russian LLaMA2-based chatbot
+
+Based on [LLaMA-2 70B fp16](https://huggingface.co/TheBloke/Llama-2-70B-fp16)
+
+This is an adapter-only version.
+
+Training code: [link](https://github.com/IlyaGusev/rulm/tree/master/self_instruct)
+
+**WARNING**: 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_70b_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 0dbd022613874fcda915f588f4a3292e137017d2
+- wandb [link](https://wandb.ai/ilyagusev/rulm_self_instruct/runs/4wp1y5jx)
+- 5 datasets: ru_turbo_alpaca, ru_sharegpt_cleaned, oasst1_ru_main_branch, gpt_roleplay_realm, ru_instruct_gpt4
+- Datasets merging script: [create_chat_set.py](https://github.com/IlyaGusev/rulm/blob/e4238fd9a196405b566a2d5838ab44b7a0f4dc31/self_instruct/src/data_processing/create_short_chat_set.py)

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/llama2-70b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dead3782b2210b8e3166e3978a19523476302fa13f937abb4da186aaba018e4
+size 262375757

generation_config.json

@@ -0,0 +1,13 @@
+{
+    "pad_token_id": 0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "temperature": 0.2,
+    "top_p": 0.9,
+    "top_k": 30,
+    "do_sample": true,
+    "max_new_tokens": 1536,
+    "num_beams": 1,
+    "repetition_penalty": 1.15,
+    "no_repeat_ngram_size": 15
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "sep_token": "<s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": null,
+  "model_max_length": 4096,
+  "pad_token": null,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}