Downloads · 30 days
119
42% of all-time downloads
OsakanaTeishoku/sarashina2.2-3b-cot-sft-20250920
sarashina2.2-3b-cot-sft-20250920 is a text generation model from OsakanaTeishoku. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
これはsbintuitions/sarashina2.2-3b-instruct-v0.1をDataPilot/ZeroSFTJav3ReasoningでSFTしたモデルです. モデルは答えの前に,思考過程を <think </think の間に出力するよう調整されています. コンテクスト長はオリジナルの8192から16384に拡張されています.
Downloads · 30 days
119
42% of all-time downloads
All-time downloads
286
Public
Parameters
3.4B
6.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors6.7 GB · 100%
From the Hugging Face model README
これはsbintuitions/sarashina2.2-3b-instruct-v0.1をDataPilot/Zero_SFT_Ja_v3_ReasoningでSFTしたモデルです.
モデルは答えの前に,思考過程を <think> </think> の間に出力するよう調整されています.
コンテクスト長はオリジナルの8192から16384に拡張されています.
unslothで以下のように推論してください.素のtransformersで推論させると出力の質が低下する問題が発生しています(2025/9/20時点で解決法がわかっていません)
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "OsakanaTeishoku/sarashina2.2-3b-cot-sft-v0.1",
max_seq_length = 16384,
load_in_4bit = False,
# token = HF_TOKEN,
)
from transformers import TextStreamer
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
# modified from https://huggingface.co/unsloth/SmolLM3-3B/blob/main/chat_template.jinja
# do not change the system prompt!!!
SYSTEM_PROMPT = "You are a helpful AI assistant. Your role as an assistant involves thoroughly exploring questions through a systematic thinking process before providing the final precise and accurate solutions. This requires engaging in a comprehensive cycle of analysis, summarizing, exploration, reassessment, reflection, backtracking, and iteration to develop well-considered thinking process. Please structure your response into two main sections: Thought and Solution using the specified format: <think> Thought section </think> Solution section. In the Thought section, detail your reasoning process in steps. Each step should include detailed considerations such as analysing questions, summarizing relevant findings, brainstorming new ideas, verifying the accuracy of the current steps, refining any errors, and revisiting previous steps. In the Solution section, based on various attempts, explorations, and reflections from the Thought section, systematically present the final solution that you deem correct. The Solution section should be logical, accurate, and concise and detail necessary steps needed to reach the conclusion."
messages = [{"role": "system", "content": SYSTEM_PROMPT},{"role": "user", "content": "what is 13 + 24 ?"},{"role": "assistant", "content": "<think>"}]
input_text = tokenizer.apply_chat_template(messages, tokenize=False, continue_final_message=True)
input = tokenizer(input_text, return_tensors="pt").to(model.device)
FastLanguageModel.for_inference(model)
output = model.generate(**input, max_new_tokens=10000, use_cache=True, do_sample=True, temperature=0.6, top_p=0.95, streamer=streamer)
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.