SeaWolf-AI (VIDRAFT

reacted to their post with 🔥 about 10 hours ago

Post

822

🧬 Introducing Darwin-9B-NEG — the first model with Native Entropy Gating (NEG)

🔗 Try it now: FINAL-Bench/Darwin-9B-NEG

We're thrilled to release Darwin-9B-NEG, a 9B-parameter reasoning model
that embeds an architecturally-internalised sense of self-confidence directly
into the transformer — our proprietary Native Entropy Gating (NEG) technology.

📊 GPQA Diamond (198 PhD-level questions):

▸ Baseline Darwin-9B (no NEG) → 51.01 %
▸ Pure NEG (greedy · 1× cost) → 63.64 % 🔥 +12.63 %p
▸ + Permutation (4× cost) → 76.26 %
▸ + Ensemble Refinement (~20×) → 84.34 % 🏆

With only 9 billion parameters and 1× inference cost, Pure NEG jumps
+12.63 %p over the same model without NEG. Going all-in with ensemble
refinement pushes it to 84.34 % — surpassing the published Qwen3.5-9B
leaderboard score (81.7 %) by +2.64 %p.

🔬 What makes NEG different from Multi-Turn Iteration (MTI)?

Classical MTI needs 3-8× extra inference passes. NEG instead lives
INSIDE the single decoding loop. Two tiny modules ride with the
transformer: NEG-Head predicts per-token entropy from the last hidden
state, and NEG-Gate conditionally restricts the top-k choice when
confidence is low. The gate activates in only 4.36 % of tokens —
essentially free at inference time.

✨ Key differentiators
• Architecturally internalised — model file *is* the feature
• 1× inference cost (vs. 3-8× for MTI)
• Drop-in with vLLM / SGLang / TGI / transformers — no extra engine
• +12.63 %p reasoning at zero latency overhead
• Single-file deployment, Apache 2.0 licensed

🧬 Lineage
Qwen/Qwen3.5-9B → Darwin-9B-Opus (V7 evolutionary merge) → Darwin-9B-NEG (V8 + NEG training)

#Darwin #NEG #NativeEntropyGating #GPQA #Reasoning #LLM #OpenSource #Apache2

posted an update about 11 hours ago

Post

822

🧬 Introducing Darwin-9B-NEG — the first model with Native Entropy Gating (NEG)

🔗 Try it now: FINAL-Bench/Darwin-9B-NEG

We're thrilled to release Darwin-9B-NEG, a 9B-parameter reasoning model
that embeds an architecturally-internalised sense of self-confidence directly
into the transformer — our proprietary Native Entropy Gating (NEG) technology.

📊 GPQA Diamond (198 PhD-level questions):

▸ Baseline Darwin-9B (no NEG) → 51.01 %
▸ Pure NEG (greedy · 1× cost) → 63.64 % 🔥 +12.63 %p
▸ + Permutation (4× cost) → 76.26 %
▸ + Ensemble Refinement (~20×) → 84.34 % 🏆

With only 9 billion parameters and 1× inference cost, Pure NEG jumps
+12.63 %p over the same model without NEG. Going all-in with ensemble
refinement pushes it to 84.34 % — surpassing the published Qwen3.5-9B
leaderboard score (81.7 %) by +2.64 %p.

🔬 What makes NEG different from Multi-Turn Iteration (MTI)?

Classical MTI needs 3-8× extra inference passes. NEG instead lives
INSIDE the single decoding loop. Two tiny modules ride with the
transformer: NEG-Head predicts per-token entropy from the last hidden
state, and NEG-Gate conditionally restricts the top-k choice when
confidence is low. The gate activates in only 4.36 % of tokens —
essentially free at inference time.

✨ Key differentiators
• Architecturally internalised — model file *is* the feature
• 1× inference cost (vs. 3-8× for MTI)
• Drop-in with vLLM / SGLang / TGI / transformers — no extra engine
• +12.63 %p reasoning at zero latency overhead
• Single-file deployment, Apache 2.0 licensed

🧬 Lineage
Qwen/Qwen3.5-9B → Darwin-9B-Opus (V7 evolutionary merge) → Darwin-9B-NEG (V8 + NEG training)

#Darwin #NEG #NativeEntropyGating #GPQA #Reasoning #LLM #OpenSource #Apache2

reacted to their post with 🔥 10 days ago

Post

4434

Darwin-TTS: 3% of an LLM's Brain Makes TTS Speak with Emotion — Zero Training

We blended 3% of Qwen3-1.7B (LLM) FFN weights into Qwen3-TTS-1.7B's talker module. The result: emotionally enhanced speech synthesis — with zero training, zero data, and zero GPU hours.

Try the Demo: FINAL-Bench/Darwin-TTS-1.7B-Cross

Model Weights: FINAL-Bench/Darwin-TTS-1.7B-Cross

Full Research Article: https://huggingface.co/blog/FINAL-Bench/darwin-tts

Qwen3-1.7B (LLM) and Qwen3-TTS-1.7B's talker share 100% identical architecture — same hidden_size (2048), same layers (28), same heads (16). This enabled pure 1:1 weight blending across 84 FFN tensors with a single lerp operation. At 3% blend, emotion appears. At 5%, emotion intensifies. At 10%, the model breaks — producing 655-second outputs for a 3-second sentence, because the LLM's "keep generating" pattern overwhelms the TTS stop signal.

To our knowledge, this is the first training-free cross-modal weight transfer between an LLM and a TTS model. Prior work either requires adapter training (SmolTolk, 2025), fine-tuning (CSLM, 2025), or massive end-to-end compute (GPT-4o). Darwin-TTS achieves cross-modal capability transfer in under 2 minutes on CPU.

The key insight: TTS models with LLM backbones already "think" in language. We're just restoring 3% of the original LLM's language understanding patterns — particularly those related to emotional semantics and prosody planning. The code is three lines: load the model, load the LLM FFN, call p.lerp_(llm_weight, 0.03).

creators of the Darwin Evolutionary Merge Framework.
Darwin LLM V7 achieved GPQA Diamond 86.9% (HF Benchmark #3)
through CMA-ES optimized FFN crossbreeding. Darwin-TTS extends this principle from LLM-to-LLM merging into cross-modal LLM-to-TTS transfer. Apache 2.0.

posted an update 10 days ago

Post

4434

Darwin-TTS: 3% of an LLM's Brain Makes TTS Speak with Emotion — Zero Training

We blended 3% of Qwen3-1.7B (LLM) FFN weights into Qwen3-TTS-1.7B's talker module. The result: emotionally enhanced speech synthesis — with zero training, zero data, and zero GPU hours.

Try the Demo: FINAL-Bench/Darwin-TTS-1.7B-Cross

Model Weights: FINAL-Bench/Darwin-TTS-1.7B-Cross

Full Research Article: https://huggingface.co/blog/FINAL-Bench/darwin-tts

Qwen3-1.7B (LLM) and Qwen3-TTS-1.7B's talker share 100% identical architecture — same hidden_size (2048), same layers (28), same heads (16). This enabled pure 1:1 weight blending across 84 FFN tensors with a single lerp operation. At 3% blend, emotion appears. At 5%, emotion intensifies. At 10%, the model breaks — producing 655-second outputs for a 3-second sentence, because the LLM's "keep generating" pattern overwhelms the TTS stop signal.

To our knowledge, this is the first training-free cross-modal weight transfer between an LLM and a TTS model. Prior work either requires adapter training (SmolTolk, 2025), fine-tuning (CSLM, 2025), or massive end-to-end compute (GPT-4o). Darwin-TTS achieves cross-modal capability transfer in under 2 minutes on CPU.

The key insight: TTS models with LLM backbones already "think" in language. We're just restoring 3% of the original LLM's language understanding patterns — particularly those related to emotional semantics and prosody planning. The code is three lines: load the model, load the LLM FFN, call p.lerp_(llm_weight, 0.03).

creators of the Darwin Evolutionary Merge Framework.
Darwin LLM V7 achieved GPQA Diamond 86.9% (HF Benchmark #3)
through CMA-ES optimized FFN crossbreeding. Darwin-TTS extends this principle from LLM-to-LLM merging into cross-modal LLM-to-TTS transfer. Apache 2.0.

reacted to their post with 🔥 12 days ago

Post

5882

🧬 Darwin-27B-Opus: 86.9% on GPQA Diamond — World #5, Zero Training
We are excited to share Darwin-27B-Opus, a 27B model that achieved 86.9% on GPQA Diamond — ranking #5 globally on the HuggingFace leaderboard — without a single gradient update.

How? Darwin breeds pretrained models through evolutionary FFN crossbreeding. The father (Qwen3.5-27B) provides the reasoning architecture; the mother (Claude 4.6 Opus Reasoning Distilled) contributes structured chain-of-thought knowledge. CMA-ES automatically discovers optimal per-layer blending ratios — no human tuning required.

The result surpasses the original Qwen3.5-27B (85.5%), GLM-5.1 (744B, 86.2%), and Qwen3.5-122B (86.6%). A 27B model outperforming 744B — with zero training, zero data, one GPU, ~2 hours.

We also confirmed hybrid vigor on Korean benchmarks: Darwin-27B-KR (2nd generation offspring) surpassed both parents on CLIcK, winning 7 out of 11 categories. The evolutionary optimizer independently assigned 93% of FFN from the Korean-specialized mother while preserving 93% of attention from the reasoning-specialized father — autonomously validating our core principle: FFN carries knowledge, Attention carries reasoning.

📊 Public release: 10 days → 300+ community derivatives, 120K+ downloads.

🔗 Links:
Darwin-27B-Opus: FINAL-Bench/Darwin-27B-Opus
article: https://huggingface.co/blog/FINAL-Bench/darwin-gpqa
Darwin Family Collection: https://huggingface.co/collections/FINAL-Bench/darwin-family

If foundation models are raw ore, Darwin is the forge. We are just getting started. 🔥

posted an update 12 days ago

Post

5882

🧬 Darwin-27B-Opus: 86.9% on GPQA Diamond — World #5, Zero Training
We are excited to share Darwin-27B-Opus, a 27B model that achieved 86.9% on GPQA Diamond — ranking #5 globally on the HuggingFace leaderboard — without a single gradient update.

How? Darwin breeds pretrained models through evolutionary FFN crossbreeding. The father (Qwen3.5-27B) provides the reasoning architecture; the mother (Claude 4.6 Opus Reasoning Distilled) contributes structured chain-of-thought knowledge. CMA-ES automatically discovers optimal per-layer blending ratios — no human tuning required.

The result surpasses the original Qwen3.5-27B (85.5%), GLM-5.1 (744B, 86.2%), and Qwen3.5-122B (86.6%). A 27B model outperforming 744B — with zero training, zero data, one GPU, ~2 hours.

We also confirmed hybrid vigor on Korean benchmarks: Darwin-27B-KR (2nd generation offspring) surpassed both parents on CLIcK, winning 7 out of 11 categories. The evolutionary optimizer independently assigned 93% of FFN from the Korean-specialized mother while preserving 93% of attention from the reasoning-specialized father — autonomously validating our core principle: FFN carries knowledge, Attention carries reasoning.

📊 Public release: 10 days → 300+ community derivatives, 120K+ downloads.

🔗 Links:
Darwin-27B-Opus: FINAL-Bench/Darwin-27B-Opus
article: https://huggingface.co/blog/FINAL-Bench/darwin-gpqa
Darwin Family Collection: https://huggingface.co/collections/FINAL-Bench/darwin-family

If foundation models are raw ore, Darwin is the forge. We are just getting started. 🔥

reacted to their post with 👀 14 days ago

Post

3009

Why This Matters — David Defeats Goliath

MODEL: FINAL-Bench/Darwin-4B-David
SPACE: FINAL-Bench/Darwin-4B-david

We're releasing Darwin-4B-David, the first second-generation model in the Darwin Opus family. By evolving an already-evolved model, it achieves 85.0% on GPQA Diamond — surpassing its 58.6% original ancestor and even gemma-4-31B (84.3%) — with just 4.5B parameters.

Second-Generation Evolution
Most merges start from a base model and produce a single offspring. Darwin-4B-David breaks this pattern. The Father (Darwin-4B-Opus) was already evolved from gemma-4-E4B-it with Claude Opus reasoning distillation — a Gen-1 model. The Mother (DavidAU's DECKARD-Expresso-Universe) brings Unsloth deep tuning across 5 in-house datasets with thinking mode by default. Crossbreeding these two produced the first Gen-2 Darwin model.

Darwin V6's Model MRI scanned both parents across all 42 layers, assigning independent optimal ratios per layer. The Mother's creativity and Korean language hotspot (Layer 22-25, weight 0.95) was maximally absorbed, while the Father's reasoning core (Layer 30-40, weight 0.48) was preserved. This is "Merge = Evolve" applied recursively — evolution of evolution.

Benchmarks
Darwin-4B-David scores 85.0% on GPQA Diamond (+26.4%p over original 58.6%), evaluated generatively with maj@8 (8 generations per question, majority vote), Epoch AI prompt format, thinking mode enabled, 50 sampled questions. On ARC-Challenge (25-shot, loglikelihood), both score 64.93% — expected, as loglikelihood doesn't capture thinking-mode reasoning differences.

Why This Matters
gemma-4-31B (30.7B) scores 84.3%. Darwin-4B-David surpasses it at 1/7th the size — no training, no RL, just 45 minutes of MRI-guided DARE-TIES on one H100. The name "David" honors Mother creator DavidAU and evokes David vs. Goliath.

posted an update 14 days ago

Post

3009

Why This Matters — David Defeats Goliath

MODEL: FINAL-Bench/Darwin-4B-David
SPACE: FINAL-Bench/Darwin-4B-david

We're releasing Darwin-4B-David, the first second-generation model in the Darwin Opus family. By evolving an already-evolved model, it achieves 85.0% on GPQA Diamond — surpassing its 58.6% original ancestor and even gemma-4-31B (84.3%) — with just 4.5B parameters.

Second-Generation Evolution
Most merges start from a base model and produce a single offspring. Darwin-4B-David breaks this pattern. The Father (Darwin-4B-Opus) was already evolved from gemma-4-E4B-it with Claude Opus reasoning distillation — a Gen-1 model. The Mother (DavidAU's DECKARD-Expresso-Universe) brings Unsloth deep tuning across 5 in-house datasets with thinking mode by default. Crossbreeding these two produced the first Gen-2 Darwin model.

Darwin V6's Model MRI scanned both parents across all 42 layers, assigning independent optimal ratios per layer. The Mother's creativity and Korean language hotspot (Layer 22-25, weight 0.95) was maximally absorbed, while the Father's reasoning core (Layer 30-40, weight 0.48) was preserved. This is "Merge = Evolve" applied recursively — evolution of evolution.

Benchmarks
Darwin-4B-David scores 85.0% on GPQA Diamond (+26.4%p over original 58.6%), evaluated generatively with maj@8 (8 generations per question, majority vote), Epoch AI prompt format, thinking mode enabled, 50 sampled questions. On ARC-Challenge (25-shot, loglikelihood), both score 64.93% — expected, as loglikelihood doesn't capture thinking-mode reasoning differences.

Why This Matters
gemma-4-31B (30.7B) scores 84.3%. Darwin-4B-David surpasses it at 1/7th the size — no training, no RL, just 45 minutes of MRI-guided DARE-TIES on one H100. The name "David" honors Mother creator DavidAU and evokes David vs. Goliath.

reacted to their post with 👍 15 days ago

Post

5547

🧬 Darwin V6: Diagnostic-Guided Evolutionary Model Merging

We are releasing Darwin-31B-Opus — a reasoning-enhanced model merging Google's Gemma-4-31B-it and TeichAI's Claude Opus Distill using the Darwin V6 engine.

Model: FINAL-Bench/Darwin-31B-Opus
Demo: FINAL-Bench/Darwin-31B-Opus

🔬 What Darwin V6 Does

Conventional merging tools (mergekit, etc.) apply a single ratio to all tensors. Set ratio=0.5 and all 1,188 tensors blend identically, with no distinction between which tensors matter for reasoning versus coding.

Darwin V6 diagnoses both parents at the tensor level before merging. It measures Shannon entropy, standard deviation, and L2 norm for every tensor, then passes 5 diagnostic probes (REASONING, CODE, MATH, KNOWLEDGE, LANGUAGE) through the model to determine layer-wise functional importance. Each of the 1,188 tensors receives an independent optimal ratio.

combined = static(entropy/std/norm) x 0.4 + probe(cosine_distance) x 0.6
final_ratio = mri_ratio x mri_trust + genome_ratio x (1 - mri_trust)

When one parent is overwhelmingly superior for a tensor (ratio < 0.15 or > 0.85), Darwin transplants it directly without interpolation. The mri_trust parameter itself is optimized by CMA-ES evolutionary search, so optimal transplant intensity is determined automatically. After merging, a Health Check compares the child against both parents layer-by-layer to detect interference or function loss.

🧬 Parent Models
Father: google/gemma-4-31B-it
Mother: TeichAI/gemma-4-31B-it-Claude-Opus-Distill

🧬 Results
Compared under identical conditions (same 50 questions, same seed, greedy, thinking mode):
Father: 60.0% (30/50)
Darwin-31B-Opus: 66.0% (33/50) — +10% relative improvement
ARC-Challenge: 82.89% (loglikelihood, zero-shot, 200 questions)
Optimal genome found by evolution:
ffn_ratio=0.93 — FFN layers strongly favor Mother (Claude Opus Distill)
block_5 (L50-L59)=0.86 and more...

11 replies

·

replied to their post 15 days ago

MRI(Model Region Imaging)
MRI stands for Model Region Imaging, a framework for scanning a black-box LLM to detect and visualize functional regions such as language, mathematics, reasoning, and coding.

reacted to their post with 🔥 16 days ago

Post

5547

🧬 Darwin V6: Diagnostic-Guided Evolutionary Model Merging

We are releasing Darwin-31B-Opus — a reasoning-enhanced model merging Google's Gemma-4-31B-it and TeichAI's Claude Opus Distill using the Darwin V6 engine.

Model: FINAL-Bench/Darwin-31B-Opus
Demo: FINAL-Bench/Darwin-31B-Opus

🔬 What Darwin V6 Does

Conventional merging tools (mergekit, etc.) apply a single ratio to all tensors. Set ratio=0.5 and all 1,188 tensors blend identically, with no distinction between which tensors matter for reasoning versus coding.

Darwin V6 diagnoses both parents at the tensor level before merging. It measures Shannon entropy, standard deviation, and L2 norm for every tensor, then passes 5 diagnostic probes (REASONING, CODE, MATH, KNOWLEDGE, LANGUAGE) through the model to determine layer-wise functional importance. Each of the 1,188 tensors receives an independent optimal ratio.

combined = static(entropy/std/norm) x 0.4 + probe(cosine_distance) x 0.6
final_ratio = mri_ratio x mri_trust + genome_ratio x (1 - mri_trust)

When one parent is overwhelmingly superior for a tensor (ratio < 0.15 or > 0.85), Darwin transplants it directly without interpolation. The mri_trust parameter itself is optimized by CMA-ES evolutionary search, so optimal transplant intensity is determined automatically. After merging, a Health Check compares the child against both parents layer-by-layer to detect interference or function loss.

🧬 Parent Models
Father: google/gemma-4-31B-it
Mother: TeichAI/gemma-4-31B-it-Claude-Opus-Distill

🧬 Results
Compared under identical conditions (same 50 questions, same seed, greedy, thinking mode):
Father: 60.0% (30/50)
Darwin-31B-Opus: 66.0% (33/50) — +10% relative improvement
ARC-Challenge: 82.89% (loglikelihood, zero-shot, 200 questions)
Optimal genome found by evolution:
ffn_ratio=0.93 — FFN layers strongly favor Mother (Claude Opus Distill)
block_5 (L50-L59)=0.86 and more...

11 replies

·

replied to their post 17 days ago

In response to community requests, I created Darwin-4B-Opus, a lightweight Gemma-4-4B-based Darwin hybrid/evolution model with reasoning enhanced through Claude Opus distillation, and released it on Hugging Face.

Model: https://huggingface.co/FINAL-Bench/Darwin-4B-Opus
Demo: https://huggingface.co/spaces/FINAL-Bench/Darwin-4B-Opus

replied to their post 17 days ago

After small models make nemotron-120

https://huggingface.co/blobbybob/Nemotron-3-Super-120B-A12B-BF16-Claude-4.6-Opus-Reasoning-Distilled

Yes, that is exactly the plan.

I will first work on the smaller Darwin models, and after that I also want to move toward a Nemotron-120 class model. Thank you for the suggestion and support.

replied to their post 17 days ago

Thank you, that is very helpful feedback.
A 1B–4B Darwin is definitely an interesting direction, especially for lightweight and local use cases.
I will seriously consider it.

replied to their post 17 days ago

We already have a smaller model here: https://huggingface.co/FINAL-Bench/Darwin-9B-Opus

Do you think an even smaller one is needed?

reacted to their post with 👀 17 days ago

Post

5547

🧬 Darwin V6: Diagnostic-Guided Evolutionary Model Merging

We are releasing Darwin-31B-Opus — a reasoning-enhanced model merging Google's Gemma-4-31B-it and TeichAI's Claude Opus Distill using the Darwin V6 engine.

Model: FINAL-Bench/Darwin-31B-Opus
Demo: FINAL-Bench/Darwin-31B-Opus

🔬 What Darwin V6 Does

Conventional merging tools (mergekit, etc.) apply a single ratio to all tensors. Set ratio=0.5 and all 1,188 tensors blend identically, with no distinction between which tensors matter for reasoning versus coding.

Darwin V6 diagnoses both parents at the tensor level before merging. It measures Shannon entropy, standard deviation, and L2 norm for every tensor, then passes 5 diagnostic probes (REASONING, CODE, MATH, KNOWLEDGE, LANGUAGE) through the model to determine layer-wise functional importance. Each of the 1,188 tensors receives an independent optimal ratio.

combined = static(entropy/std/norm) x 0.4 + probe(cosine_distance) x 0.6
final_ratio = mri_ratio x mri_trust + genome_ratio x (1 - mri_trust)

When one parent is overwhelmingly superior for a tensor (ratio < 0.15 or > 0.85), Darwin transplants it directly without interpolation. The mri_trust parameter itself is optimized by CMA-ES evolutionary search, so optimal transplant intensity is determined automatically. After merging, a Health Check compares the child against both parents layer-by-layer to detect interference or function loss.

🧬 Parent Models
Father: google/gemma-4-31B-it
Mother: TeichAI/gemma-4-31B-it-Claude-Opus-Distill

🧬 Results
Compared under identical conditions (same 50 questions, same seed, greedy, thinking mode):
Father: 60.0% (30/50)
Darwin-31B-Opus: 66.0% (33/50) — +10% relative improvement
ARC-Challenge: 82.89% (loglikelihood, zero-shot, 200 questions)
Optimal genome found by evolution:
ffn_ratio=0.93 — FFN layers strongly favor Mother (Claude Opus Distill)
block_5 (L50-L59)=0.86 and more...

11 replies

·

posted an update 17 days ago

Post

5547

🧬 Darwin V6: Diagnostic-Guided Evolutionary Model Merging

We are releasing Darwin-31B-Opus — a reasoning-enhanced model merging Google's Gemma-4-31B-it and TeichAI's Claude Opus Distill using the Darwin V6 engine.

Model: FINAL-Bench/Darwin-31B-Opus
Demo: FINAL-Bench/Darwin-31B-Opus

🔬 What Darwin V6 Does

Conventional merging tools (mergekit, etc.) apply a single ratio to all tensors. Set ratio=0.5 and all 1,188 tensors blend identically, with no distinction between which tensors matter for reasoning versus coding.

Darwin V6 diagnoses both parents at the tensor level before merging. It measures Shannon entropy, standard deviation, and L2 norm for every tensor, then passes 5 diagnostic probes (REASONING, CODE, MATH, KNOWLEDGE, LANGUAGE) through the model to determine layer-wise functional importance. Each of the 1,188 tensors receives an independent optimal ratio.

combined = static(entropy/std/norm) x 0.4 + probe(cosine_distance) x 0.6
final_ratio = mri_ratio x mri_trust + genome_ratio x (1 - mri_trust)

When one parent is overwhelmingly superior for a tensor (ratio < 0.15 or > 0.85), Darwin transplants it directly without interpolation. The mri_trust parameter itself is optimized by CMA-ES evolutionary search, so optimal transplant intensity is determined automatically. After merging, a Health Check compares the child against both parents layer-by-layer to detect interference or function loss.

🧬 Parent Models
Father: google/gemma-4-31B-it
Mother: TeichAI/gemma-4-31B-it-Claude-Opus-Distill

🧬 Results
Compared under identical conditions (same 50 questions, same seed, greedy, thinking mode):
Father: 60.0% (30/50)
Darwin-31B-Opus: 66.0% (33/50) — +10% relative improvement
ARC-Challenge: 82.89% (loglikelihood, zero-shot, 200 questions)
Optimal genome found by evolution:
ffn_ratio=0.93 — FFN layers strongly favor Mother (Claude Opus Distill)
block_5 (L50-L59)=0.86 and more...

11 replies

·

reacted to their post with 🔥 22 days ago

Post

3148

💎 Gemma 4 Playground — Dual Model Demo on ZeroGPU

We just launched a Gemma 4 Playground that lets you chat with Google DeepMind's latest open models — directly on Hugging Face Spaces with ZeroGPU.

FINAL-Bench/Gemma-4-Multi

👉 Try it now: FINAL-Bench/Gemma-4-Multi
Two Models, One Space
Switch between both Gemma 4 variants in a single interface:

⚡ Gemma 4 26B-A4B — MoE with 128 experts, only 3.8B active params. 95% of the 31B's quality at ~8x faster inference. AIME 88.3%, GPQA 82.3%.
🏆 Gemma 4 31B — Dense 30.7B. Best quality among Gemma 4 family. AIME 89.2%, GPQA 84.3%, Codeforces 2150. Arena open-model top 3.

Features

Vision — Upload images for analysis, OCR, chart reading, document parsing
Thinking Mode — Toggle chain-of-thought reasoning with Gemma 4's native <|channel> thinking tokens
System Prompts — 6 presets (General, Code, Math, Creative, Translate, Research) or write your own
Streaming — Real-time token-by-token response via ZeroGPU
Apache 2.0 — Fully open, no restrictions

Technical Details
Built with the dev build of transformers (5.5.0.dev0) for full Gemma 4 support including multimodal apply_chat_template, variable-resolution image processing, and native thinking mode. Runs on HF ZeroGPU with @spaces .GPU — no dedicated GPU needed.
Both models support 256K context window and 140+ languages out of the box.

Links

- 🤗 Space: [FINAL-Bench/Gemma-4-Multi]( FINAL-Bench/Gemma-4-Multi)
- 📄 Gemma 4 26B-A4B: [google/gemma-4-26B-A4B-it]( google/gemma-4-26B-A4B-it)
- 📄 Gemma 4 31B: [google/gemma-4-31B-it]( google/gemma-4-31B-it)
- 🔬 DeepMind Blog: [Gemma 4 Launch](https://deepmind.google/blog/gemma-4-byte-for-byte-the-most-capable-open-models/)

posted an update 22 days ago

Post

3148

💎 Gemma 4 Playground — Dual Model Demo on ZeroGPU

We just launched a Gemma 4 Playground that lets you chat with Google DeepMind's latest open models — directly on Hugging Face Spaces with ZeroGPU.

FINAL-Bench/Gemma-4-Multi

👉 Try it now: FINAL-Bench/Gemma-4-Multi
Two Models, One Space
Switch between both Gemma 4 variants in a single interface:

⚡ Gemma 4 26B-A4B — MoE with 128 experts, only 3.8B active params. 95% of the 31B's quality at ~8x faster inference. AIME 88.3%, GPQA 82.3%.
🏆 Gemma 4 31B — Dense 30.7B. Best quality among Gemma 4 family. AIME 89.2%, GPQA 84.3%, Codeforces 2150. Arena open-model top 3.

Features

Vision — Upload images for analysis, OCR, chart reading, document parsing
Thinking Mode — Toggle chain-of-thought reasoning with Gemma 4's native <|channel> thinking tokens
System Prompts — 6 presets (General, Code, Math, Creative, Translate, Research) or write your own
Streaming — Real-time token-by-token response via ZeroGPU
Apache 2.0 — Fully open, no restrictions

Technical Details
Built with the dev build of transformers (5.5.0.dev0) for full Gemma 4 support including multimodal apply_chat_template, variable-resolution image processing, and native thinking mode. Runs on HF ZeroGPU with @spaces .GPU — no dedicated GPU needed.
Both models support 256K context window and 140+ languages out of the box.

Links

- 🤗 Space: [FINAL-Bench/Gemma-4-Multi]( FINAL-Bench/Gemma-4-Multi)
- 📄 Gemma 4 26B-A4B: [google/gemma-4-26B-A4B-it]( google/gemma-4-26B-A4B-it)
- 📄 Gemma 4 31B: [google/gemma-4-31B-it]( google/gemma-4-31B-it)
- 🔬 DeepMind Blog: [Gemma 4 Launch](https://deepmind.google/blog/gemma-4-byte-for-byte-the-most-capable-open-models/)

replied to their post 22 days ago

Good stuff. That actually sounds kind of interesting.

Just the least you could do is write the model card yourselves such that you catch these things. I only continued reading because I was like "wait I think I might see the vision" but nothing came of it. That's why I got so frustrated. The least we can do for each other is read the things we post. I'd be pretty disappointed if the model card sold my work short so hard.

I acknowledge I went a little far, it's just tiring to be in this space sometimes.

Looking forward to the detailed report.

Appreciate the honesty, and the critique was deserved. The model card has been rewritten with proper technical definitions and methodology. MMLU-Pro results are in progress and will be published soon. Thanks for pushing us to do better.

VIDRAFT_LAB

AI & ML interests

Recent Activity

Organizations

VIDRAFT_LAB

AI & ML interests

Recent Activity

Organizations

SeaWolf-AI's activity