FINAL-Bench / lastbrain

huggingface.co
Total runs: 8
24-hour runs: 0
7-day runs: -2
30-day runs: -10
Model's Last Updated: April 18 2026
text-generation

Introduction of lastbrain

Model Details of lastbrain

๐Ÿง  lastbrain โ€” Darwin V8

Darwin V8 ๊ธฐ๋ฐ˜ Claude Opus ์ฆ๋ฅ˜ ๋ชจ๋ธ (2B ํŒŒ๋ผ๋ฏธํ„ฐ)


๐Ÿ“ฆ ํŠน์ง•
  • Base : Qwen3.5-2B (2.3B ํŒŒ๋ผ๋ฏธํ„ฐ, ํ•˜์ด๋ธŒ๋ฆฌ๋“œ ์–ดํ…์…˜)
  • Training : SFT + LoRA ( all-linear , rank=16, ฮฑ=32)
  • Teachers : Claude Opus 4.5 / 4.6, Claude Sonnet 4.6 (pre-generated reasoning traces)
  • Data : 4,451 ๊ณ ํ’ˆ์งˆ ์ถ”๋ก  ๊ถค์  (4๊ฐœ ๊ณต๊ฐœ ๋ฐ์ดํ„ฐ์…‹)
  • Merged : LoRA ์–ด๋Œ‘ํ„ฐ๊ฐ€ base ๊ฐ€์ค‘์น˜์— ์™„์ „ ํ†ตํ•ฉ๋˜์–ด ๋…๋ฆฝ ์‹คํ–‰ ๊ฐ€๋Šฅ

๐Ÿš€ ๋น ๋ฅธ ์‚ฌ์šฉ๋ฒ•
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "FINAL-Bench/lastbrain"
tok = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True
)

messages = [
    {"role": "user", "content": "If a train travels 60 km in 45 minutes, what is its speed in km/h?"}
]
prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tok(prompt, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=800,
        do_sample=False,
        pad_token_id=tok.eos_token_id,
    )
print(tok.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

์˜ˆ์‹œ ์ถœ๋ ฅ :

To find the speed of the train in km/h, we need to convert the given time from minutes to hours.

**Given:**
- Distance = 60 km
- Time = 45 minutes

**Step 1: Convert time to hours**
Since there are 60 minutes in 1 hour:
Timeย inย hours=4560=0.75ย hours\text{Time in hours} = \frac{45}{60} = 0.75 \text{ hours}

**Step 2: Calculate speed**
Speed=600.75=80ย km/h\text{Speed} = \frac{60}{0.75} = 80 \text{ km/h}

**Final Answer:** The speed of the train is **80 km/h**.

๐Ÿงฌ Darwin V8 ํ•™์Šต ํŒŒ์ดํ”„๋ผ์ธ
[Qwen/Qwen3.5-2B] โ”€โ”€โ”€โ”€ Base ๋ชจ๋ธ (๋™๊ฒฐ)
        +
[4,451 Claude Opus/Sonnet reasoning traces]
        โ†“
[SFT Training]
  - LoRA (all-linear, r=16, ฮฑ=32)
  - Learning rate: 2e-4 (V8 rule: ร—10 FullFT)
  - 2 epochs, bf16, 8ร—B200 DDP
  - Loss: 1.33 โ†’ 1.10 (-17%)
  - Token accuracy: 68% โ†’ 72% (+4%p)
        โ†“
[LoRA merge into base weights]
        โ†“
[lastbrain] โ† ์ด ๋ชจ๋ธ

๐Ÿ“Š ํ•™์Šต ๋ฐ์ดํ„ฐ ๊ตฌ์„ฑ
๋ฐ์ดํ„ฐ์…‹ ์ƒ˜ํ”Œ ์ˆ˜ ์ถœ์ฒ˜ Teacher
nohurry/Opus-4.6-Reasoning-3000x-filtered 2,326 Claude Opus 4.6
TeichAI/Claude-Opus-4.6-Reasoning-887x 887 Claude Opus 4.6
TeichAI/claude-4.5-opus-high-reasoning-250x 250 Claude Opus 4.5
TeichAI/Claude-Sonnet-4.6-Reasoning-1100x 1,100 Claude Sonnet 4.6
ํ•ฉ๊ณ„ (ํ•„ํ„ฐ ํ›„) 4,451 -

๐ŸŽฏ ์„ค๊ณ„ ์ฒ ํ•™ (Darwin V8)
  1. LoRA Without Regret โ€” all-linear target, high LR, ์ž‘์€ rank๋„ OK
  2. Response Distillation โ€” pre-generated Opus traces๋กœ ๋น„์šฉ ํšจ์œจ์  ์ฆ๋ฅ˜
  3. Merge-and-Deploy โ€” LoRA ์–ด๋Œ‘ํ„ฐ ํ†ตํ•ฉ ํ›„ ์ถ”๊ฐ€ ์˜์กด์„ฑ ์—†์ด ๋ฐฐํฌ

๐Ÿ” ์žฌํ˜„ ๋ฐฉ๋ฒ•

์ด ๋ชจ๋ธ์€ ๋‹ค์Œ ๋‘ ์ปดํฌ๋„ŒํŠธ๋ฅผ mergeํ•˜์—ฌ ๋งŒ๋“ค์–ด์กŒ์Šต๋‹ˆ๋‹ค:

from transformers import AutoModelForCausalLM
from peft import PeftModel
import torch

base = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3.5-2B", torch_dtype=torch.bfloat16
)
model = PeftModel.from_pretrained(
    base, "FINAL-Bench/Qwen3.5-2B-Opus-Distill-v1"
)
merged = model.merge_and_unload()
merged.save_pretrained("./lastbrain")

๐Ÿ“ ์ƒ˜ํ”Œ ํ…Œ์ŠคํŠธ ๊ฒฐ๊ณผ (4๋ฌธ์ œ)
์œ ํ˜• ์ •๋‹ต ์—ฌ๋ถ€ ์‘๋‹ต ๊ธธ์ด
Math (๊ธฐ์ฐจ ์†๋„) โœ… 80 km/h 771์ž
Logic (ํ‚ค ๋น„๊ต) โœ… Carol 354์ž
Code (์†Œ์ˆ˜ ํŒ๋ณ„) โœ… Python ํ•จ์ˆ˜ 1,712์ž
Korean (์ตœ์ €์‹œ๊ธ‰) โœ… 1,577,600์› 142์ž

Markdown/LaTeX/Step-by-Step ๊ตฌ์กฐํ™”๋œ ๋‹ต๋ณ€ ์ž์—ฐ์Šค๋Ÿฝ๊ฒŒ ์ƒ์„ฑ


โš ๏ธ ์ œํ•œ ์‚ฌํ•ญ
  • ๊ทœ๋ชจ : 2.3B ํŒŒ๋ผ๋ฏธํ„ฐ (์†Œํ˜• ๋ชจ๋ธ)
  • ํ•œ๊ตญ์–ด ๊ณ„์‚ฐ ์ •ํ™•์„ฑ : ๋•Œ๋กœ ์ˆซ์ž ์˜ค๋ฅ˜ ๋ฐœ์ƒ ๊ฐ€๋Šฅ (์†Œํ˜• ๋ชจ๋ธ ํ•œ๊ณ„)
  • ๊ธด ์ปจํ…์ŠคํŠธ : ํ•™์Šต ์‹œ max_length=4,096์œผ๋กœ ํ•™์Šต๋จ
  • <think> ํƒœ๊ทธ : ๋ช…์‹œ์  ์‚ฌ์šฉ ๋‚ฎ์Œ (reasoning์„ ๋ณธ๋ฌธ์— ํ†ตํ•ฉ)

๐Ÿชช ๋ผ์ด์„ ์Šค
  • Base model: Apache 2.0 (Qwen)
  • ํ•™์Šต ๋ฐ์ดํ„ฐ: ๊ฐ ๋ฐ์ดํ„ฐ์…‹ ๊ฐœ๋ณ„ ๋ผ์ด์„ ์Šค ์ฐธ์กฐ
  • ์ด ๋ชจ๋ธ: Apache 2.0

๐Ÿ™ ํฌ๋ ˆ๋”ง
  • Base : Qwen team (Alibaba)
  • Teacher : Anthropic (Claude Opus 4.5/4.6, Sonnet 4.6)
  • ๋ฐ์ดํ„ฐ ๊ณต๊ฐœ : nohurry, TeichAI
  • Training & Release : FINAL-Bench / VIDRAFT_LAB

๐Ÿ”— ๊ด€๋ จ ๋ชจ๋ธ

Darwin V8 ยท Part of the evolutionary model merging series by VIDRAFT_LAB

Runs of FINAL-Bench lastbrain on huggingface.co

8
Total runs
0
24-hour runs
0
3-day runs
-2
7-day runs
-10
30-day runs

More Information About lastbrain huggingface.co Model

More lastbrain license Visit here:

https://choosealicense.com/licenses/apache-2.0

lastbrain huggingface.co

lastbrain huggingface.co is an AI model on huggingface.co that provides lastbrain's model effect (), which can be used instantly with this FINAL-Bench lastbrain model. huggingface.co supports a free trial of the lastbrain model, and also provides paid use of the lastbrain. Support call lastbrain model through api, including Node.js, Python, http.

FINAL-Bench lastbrain online free

lastbrain huggingface.co is an online trial and call api platform, which integrates lastbrain's modeling effects, including api services, and provides a free online trial of lastbrain, you can try lastbrain online for free by clicking the link below.

FINAL-Bench lastbrain online free url in huggingface.co:

https://huggingface.co/FINAL-Bench/lastbrain

lastbrain install

lastbrain is an open source model from GitHub that offers a free installation service, and any user can find lastbrain on GitHub to install. At the same time, huggingface.co provides the effect of lastbrain install, users can directly use lastbrain installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

lastbrain install url in huggingface.co:

https://huggingface.co/FINAL-Bench/lastbrain

Url of lastbrain

Provider of lastbrain huggingface.co

FINAL-Bench
ORGANIZATIONS

Other API from FINAL-Bench