VIDRAFT AI Media
📰
17
Open models, self-improving AI and decision AI, measured
AIQ
aiqcamp
AI & ML interests
None yet
Recent Activity
liked a Space 1 day ago
VIDraft/ai-media liked a model 1 day ago
FINAL-Bench/VKORE-46M-NPU reacted to SeaWolf-AI's post with 🚀 1 day ago
🚀 We pretrained a language model from scratch on an inference-only NPU, with real backpropagation.
🤗 Model: https://huggingface.co/FINAL-Bench/VKORE-46M-NPU 📝 Technical write-up: https://huggingface.co/blog/FINAL-Bench/backpropagation-on-an-inference-only-npu-pretraini
"NPUs are inference-only, you can't train on them." We built a counterexample: VKORE-46M-NPU, trained from scratch on a first-gen (2025) inference NPU, 32 chips, no pretrained weights. A 46M decoder-only model (RoPE · SwiGLU · RMSNorm · GQA), char-level, TinyStories.
📏 Why trust it: a falling-loss curve proves nothing. So we trained the same model under identical init, data, and schedule on the NPU and on a GPU reference. · Loss trajectories correlate at 0.99 · Throughput converged to a comparable level The NPU backward pass and optimizer updates do numerically the same work as the GPU, not an approximation that merely trends down.
🧩 One accelerator now covers pretraining · LoRA · inference · quantization. We call this layer VKORE: "CUDA for NPUs."
⚖️ Public: weights, model card, NPU-vs-GPU comparison. Private (patent-pending, paper to follow): the core training technique. 46M char-level is toy scale on purpose: it proves the training path, not model quality. Larger models and real data are next.
Feedback from folks working on custom autograd backends and low-precision training kernels on non-GPU accelerators is very welcome. 🙌Organizations
liked a
Space 1 day ago
liked a
model 1 day ago
reacted to SeaWolf-AI's post with 🚀 1 day ago
Post
1,964
🚀 We pretrained a language model from scratch on an inference-only NPU, with real backpropagation.
🤗 Model: FINAL-Bench/VKORE-46M-NPU 📝 Technical write-up: https://huggingface.co/blog/FINAL-Bench/backpropagation-on-an-inference-only-npu-pretraini
"NPUs are inference-only, you can't train on them." We built a counterexample: VKORE-46M-NPU, trained from scratch on a first-gen (2025) inference NPU, 32 chips, no pretrained weights. A 46M decoder-only model (RoPE · SwiGLU · RMSNorm · GQA), char-level, TinyStories.
📏 Why trust it: a falling-loss curve proves nothing. So we trained the same model under identical init, data, and schedule on the NPU and on a GPU reference. · Loss trajectories correlate at 0.99 · Throughput converged to a comparable level The NPU backward pass and optimizer updates do numerically the same work as the GPU, not an approximation that merely trends down.
🧩 One accelerator now covers pretraining · LoRA · inference · quantization. We call this layer VKORE: "CUDA for NPUs."
⚖️ Public: weights, model card, NPU-vs-GPU comparison. Private (patent-pending, paper to follow): the core training technique. 46M char-level is toy scale on purpose: it proves the training path, not model quality. Larger models and real data are next.
Feedback from folks working on custom autograd backends and low-precision training kernels on non-GPU accelerators is very welcome. 🙌
🤗 Model: FINAL-Bench/VKORE-46M-NPU 📝 Technical write-up: https://huggingface.co/blog/FINAL-Bench/backpropagation-on-an-inference-only-npu-pretraini
"NPUs are inference-only, you can't train on them." We built a counterexample: VKORE-46M-NPU, trained from scratch on a first-gen (2025) inference NPU, 32 chips, no pretrained weights. A 46M decoder-only model (RoPE · SwiGLU · RMSNorm · GQA), char-level, TinyStories.
📏 Why trust it: a falling-loss curve proves nothing. So we trained the same model under identical init, data, and schedule on the NPU and on a GPU reference. · Loss trajectories correlate at 0.99 · Throughput converged to a comparable level The NPU backward pass and optimizer updates do numerically the same work as the GPU, not an approximation that merely trends down.
🧩 One accelerator now covers pretraining · LoRA · inference · quantization. We call this layer VKORE: "CUDA for NPUs."
⚖️ Public: weights, model card, NPU-vs-GPU comparison. Private (patent-pending, paper to follow): the core training technique. 46M char-level is toy scale on purpose: it proves the training path, not model quality. Larger models and real data are next.
Feedback from folks working on custom autograd backends and low-precision training kernels on non-GPU accelerators is very welcome. 🙌
- 9 replies
liked 3
Spaces 5 days ago
liked a
Space 6 days ago
reacted to SeaWolf-AI's post with 🚀🔥 7 days ago
Post
4,111
🏆 Darwin-27B-ZTC-v2 just took #1 on the System One Mosaic Benchmark (S1MB).
S1MB compares 102 models across 137 specialized benchmarks, in three task types: Noul (assess a condition), Choice (select an option), Score (rate on a scale). Ranking is by overall Borda score.
📊 Top of the board
🥇 Darwin ZTC v2 (FINAL-Bench) 89.58
🥈 OpenJev-27B 87.50
🥉 AutoJev-27B 87.07
4️⃣ Eikos 27B 85.43
5️⃣ Jev 1.13 85.05
🔎 Ranks 2 to 5 are all the JEV family (TypeSafe AI's System One model, from ex-OpenAI researchers). S1MB exists to compare these System One judges, so leading it is the headline.
⚙️ Why a zero-token judge wins here
🔹 It does not generate. It reads the input and typed questions and returns a calibrated distribution in a single forward pass.
🔹 Zero generated tokens, no decoding loop, so latency and cost stay low.
🔹 Holds up out of distribution too: General Noul 96.00, General Choice 99.34.
It is also #1 on the typed-decisions leaderboard (0.743, zero-shot). Same message from both: a deterministic, calibrated judge at one forward pass per call.
🔗 Model: FINAL-Bench/Darwin-27B-ZTC-v2
🔗 Leaderboard: hotchpotch/S1MB-leaderboard
Standings move as new models are added. Numbers reflect the board at the time of writing. 🙌
S1MB compares 102 models across 137 specialized benchmarks, in three task types: Noul (assess a condition), Choice (select an option), Score (rate on a scale). Ranking is by overall Borda score.
📊 Top of the board
🥇 Darwin ZTC v2 (FINAL-Bench) 89.58
🥈 OpenJev-27B 87.50
🥉 AutoJev-27B 87.07
4️⃣ Eikos 27B 85.43
5️⃣ Jev 1.13 85.05
🔎 Ranks 2 to 5 are all the JEV family (TypeSafe AI's System One model, from ex-OpenAI researchers). S1MB exists to compare these System One judges, so leading it is the headline.
⚙️ Why a zero-token judge wins here
🔹 It does not generate. It reads the input and typed questions and returns a calibrated distribution in a single forward pass.
🔹 Zero generated tokens, no decoding loop, so latency and cost stay low.
🔹 Holds up out of distribution too: General Noul 96.00, General Choice 99.34.
It is also #1 on the typed-decisions leaderboard (0.743, zero-shot). Same message from both: a deterministic, calibrated judge at one forward pass per call.
🔗 Model: FINAL-Bench/Darwin-27B-ZTC-v2
🔗 Leaderboard: hotchpotch/S1MB-leaderboard
Standings move as new models are added. Numbers reflect the board at the time of writing. 🙌
liked a
model 7 days ago
liked a
Space 7 days ago
liked a
dataset 8 days ago
liked a
model 8 days ago
liked a
Space 11 days ago
reacted to SeaWolf-AI's post with 👀🤗❤️👍 11 days ago
Post
6,243
💻 Data-center AI, now on a laptop: POCKET-Darwin-180B
We're releasing a 4-bit GGUF build of Darwin-180B-RSI, #1 on seven official Hugging Face leaderboards (self-reported), that runs without a GPU.
📦 360 GB → 111 GB (4-bit GGUF, 4 files)
🖥️ No GPU: one server CPU (16 threads) at 18.4–21.0 tokens/s
💻 RTX 5060 laptop (8 GB VRAM) + 32 GB RAM: 4.17 tokens/s
🧊 128 GB mini PC: whole model in memory, no GPU needed
🎯 MMLU-Pro, 2,000 questions, paired: original 87.65% = 4-bit 87.65%
How?
· Only ~3B of 180B parameters are active per token (10 of 512 experts)
· llama.cpp streams just the needed experts from SSD, so 32 GB RAM is enough
· Graft quantization: we took the proven Unsloth UD-Q4_K_XL base build and swapped in only the 300 tensors our RSI training changed (300/300 verified)
Under the hood is Model-level Recursive Self-Improvement. The model solves verifiable problems, keeps only its own solutions that check out as correct, and trains on them. No human-written solutions or reasoning traces.
Built for teams that can't send data to an external cloud (defense, finance, public sector) to run a top-tier model fully offline.
📝 Article: https://huggingface.co/blog/FINAL-Bench/data-center-ai-now-on-a-laptop-pocket-darwin-180b
🤗 Model: FINAL-Bench/POCKET-Darwin-180B-GGUF
🧬 Original: FINAL-Bench/Darwin-180B-RSI
#Darwin #RSI #GGUF #llamacpp #OnDevice #MoE
We're releasing a 4-bit GGUF build of Darwin-180B-RSI, #1 on seven official Hugging Face leaderboards (self-reported), that runs without a GPU.
📦 360 GB → 111 GB (4-bit GGUF, 4 files)
🖥️ No GPU: one server CPU (16 threads) at 18.4–21.0 tokens/s
💻 RTX 5060 laptop (8 GB VRAM) + 32 GB RAM: 4.17 tokens/s
🧊 128 GB mini PC: whole model in memory, no GPU needed
🎯 MMLU-Pro, 2,000 questions, paired: original 87.65% = 4-bit 87.65%
How?
· Only ~3B of 180B parameters are active per token (10 of 512 experts)
· llama.cpp streams just the needed experts from SSD, so 32 GB RAM is enough
· Graft quantization: we took the proven Unsloth UD-Q4_K_XL base build and swapped in only the 300 tensors our RSI training changed (300/300 verified)
Under the hood is Model-level Recursive Self-Improvement. The model solves verifiable problems, keeps only its own solutions that check out as correct, and trains on them. No human-written solutions or reasoning traces.
Built for teams that can't send data to an external cloud (defense, finance, public sector) to run a top-tier model fully offline.
📝 Article: https://huggingface.co/blog/FINAL-Bench/data-center-ai-now-on-a-laptop-pocket-darwin-180b
🤗 Model: FINAL-Bench/POCKET-Darwin-180B-GGUF
🧬 Original: FINAL-Bench/Darwin-180B-RSI
#Darwin #RSI #GGUF #llamacpp #OnDevice #MoE
- 30 replies
liked a
model 14 days ago
liked a
Space 16 days ago