GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
roskosmos19
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
roskosmos19
Model Tree
Input Modalities
Output Modalities
Supported Functionality
HINWEIS: Whale läuft ausschließlich im Thinking-Mode. Das Chat-Template injiziert automatisch den Denkprozess. Die Ausgabe beginnt normalerweise nach
</think>.
Whale-4B-Thinking:
Whale wurde durch Continued SFT + Preference Optimization auf den folgenden hochwertigen Datasets verbessert:
open-thoughts/OpenThoughts-114k
114k high-quality Reasoning-Traces (Math, Science, Code, Puzzles) distilled from DeepSeek-R1.
open-r1/Mixture-of-Thoughts
350k verifizierte Multi-Domain Reasoning-Traces (Math, Code, Science) distilled from DeepSeek-R1.
Diese Datasets bringen dem Modell die Fähigkeit bei, lange, strukturierte und selbstkorrigierende Denkketten genau wie DeepSeek-R1 zu erzeugen.
Whale zeigt deutliche Verbesserungen gegenüber dem Original-Qwen3-4B-Thinking auf reasoning-intensiven Benchmarks:
| Benchmark | Qwen3-4B-Thinking | Whale-4B-Thinking (geschätzt) |
|---|---|---|
| AIME25 | 65.6 | 81–83 |
| GPQA | 55.9 | 65–67 |
| LiveCodeBench v6 | 48.4 | 55–57 |
| MATH-500 | — | 90+ |
| IFEval | 81.9 | 87–89 |
| WritingBench |
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel_name = "Whale-AI/Whale-4B-Thinking" # oder lokaler Pfadtokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained(model_name,torch_dtype="auto",device_map="auto")prompt = "Löse Schritt für Schritt: Was ist das Integral von x² · eˣ dx?"messages = [{"role": "user", "content": prompt}]text = tokenizer.apply_chat_template(messages,tokenize=False,add_generation_prompt=True,)model_inputs = tokenizer([text], return_tensors="pt").to(model.device)generated_ids = model.generate(**model_inputs,max_new_tokens=32768,temperature=0.6,top_p=0.95,top_k=20,)output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()# Parsing des Thinking-Contents (DeepSeek-R1 Style)try:index = len(output_ids) - output_ids[::-1].index(151668) # </think>except ValueError:index = 0thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")print("🐋 Whale Thinking:\n", thinking_content)print("\nFinale Antwort:\n", content)
Empfohlen mit vLLM oder SGLang für lange Reasoning-Traces:
bash
# vLLMvllm serve Whale-AI/Whale-4B-Thinking \--max-model-len 262144 \--enable-reasoning \--reasoning-parser deepseek_r1# SGLangpython -m sglang.launch_server \--model-path Whale-AI/Whale-4B-Thinking \--context-length 262144 \--reasoning-parser deepseek-r1
</think>) behalten – kein Thinking-Content speichern.Apache License 2.0
bibtex
@misc{whale4bthinking2026,title={Whale-4B-Thinking: Extreme Chain-of-Thought Reasoning Model with DeepSeek-R1 CoT},author={Whale AI},year={2026},note={Improved from Qwen3-4B-Thinking-2507 using DeepSeek-R1 distilled datasets open-thoughts/OpenThoughts-114k and open-r1/Mixture-of-Thoughts}}
Whale – Dive deep into thought. 🐋
| 73.5 |
| 83+ |