Create README.md

README.md

@@ -0,0 +1,101 @@
+---
+license: apache-2.0
+language:
+- en
+- ru
+---
+
+# Saiga2-13B-4bit
+This files are GPTQ model files for [saiga2-13B-lora](https://huggingface.co/IlyaGusev/saiga2_13b_lora) model.
+
+## Technical details
+Model was quantized to 4-bit with [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) library
+
+## Examples of usage
+First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed:
+
+GITHUB_ACTIONS=true pip install auto-gptq
+
+Then try the following example code:
+
+```python
+from transformers import AutoTokenizer, TextGenerationPipeline
+from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
+
+
+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()
+
+
+MODEL_NAME = "gurgutan/saiga2-13b-4bit"
+DEFAULT_MESSAGE_TEMPLATE = "<s>{role}\n{content}</s>\n"
+DEFAULT_SYSTEM_PROMPT = "Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им."
+
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=True)
+model = AutoGPTQForCausalLM.from_quantized(MODEL_NAME, device="cuda:0", use_safetensors=True, use_triton=False)
+generation_config = GenerationConfig.from_pretrained(MODEL_NAME)
+model.eval()
+
+input = "Сочини стих, который начинается словами: Буря мглою небо кроет"
+conversation = Conversation()
+conversation.add_user_message(input)
+prompt = conversation.get_prompt(tokenizer)
+output = generate(model, tokenizer, prompt, generation_config)
+print(inp)
+print(output)
+
+```
+# Original model: [saiga2-13B-lora](https://huggingface.co/IlyaGusev/saiga2_13b_lora)
+Модель ассистента на основе LLaMA2 дообученная на русскоязычных наборах. Модель имеет 13 млрд. параметров.