Update README.md

README.md

@@ -1 +1,92 @@
-Steps = 50004step
+---
+license: apache-2.0
+license_name: tongyi-qianwen-license-agreement
+license_link: >-
+  https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
+datasets:
+- oscar-corpus/OSCAR-2301
+- mc4
+language:
+- ja
+---
+
+<p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/64c8a2e01c25d2c581a381c1/9CbN4lDGU42c-7DmK_mGM.png" alt="drawing" width="600"/>
+</p>
+
+TinyLlama + Japanese pre-training (50,004 steps)
+
+# How to use
+
+
+### Hugggingface
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("lightblue/karasu-1.1B")
+model = AutoModelForCausalLM.from_pretrained("lightblue/karasu-1.1B", torch_dtype=torch.bfloat16, device_map="auto")
+
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+messages = [{"role": "system", "content": "あなたはAIアシスタントです。"}]
+messages.append({"role": "user", "content": "イギリスの首相は誰ですか？"})
+
+prompt = tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)
+
+pipe(prompt, max_new_tokens=100, do_sample=False, temperature=0.0, return_full_text=False)
+```
+
+
+### VLLM
+```python
+from vllm import LLM, SamplingParams
+
+sampling_params = SamplingParams(temperature=0.0, max_tokens=100)
+llm = LLM(model="lightblue/karasu-1.1B")
+
+messages = [{"role": "system", "content": "あなたはAIアシスタントです。"}]
+messages.append({"role": "user", "content": "イギリスの首相は誰ですか？"})
+prompt = llm.llm_engine.tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)
+prompts = [prompt]
+
+outputs = llm.generate(prompts, sampling_params)
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+```
+
+
+
+# Base checkpoint
+[Qwen/Qwen-14B-Chat](TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T)
+
+# Training datasets (total ~3B)
+A filtered then sampled set from
+* OSCAR (Japanese)
+* mC4 (Japanese)
+
+# Developed by
+
+<a href="https://www.lightblue-tech.com">
+<img src="https://www.lightblue-tech.com/wp-content/uploads/2023/08/color_%E6%A8%AA%E5%9E%8B-1536x469.png" alt="Lightblue technology logo" width="400"/>
+</a>
+
+### Engineers
+Peter Devine
+
+Sho Higuchi
+
+### Advisors
+Yuuki Yamanaka 
+
+Atom Sonoda
+
+### Project manager
+Shunichi Taniguchi
+
+Tomioka Wataru
+
+### Dataset evaluator
+Renju Aoki