模型類型: LoRA Adapter (SFT + ORPO 累積更新) - 基礎模型: unsloth/Qwen3-4B-Base-unsloth-bnb-4bit - SFT 模型來源: tatasauce4life/qwen3-4b-en2zh-lora - 訓練方法: ORPO (Odds Ratio Preference Optimization) 1. SFT 階段: 使用英中平行小說語料做 LoRA SFT 2. ORPO 階段: 使用人工譯文 (chosen) vs. 機器翻譯 (rejected) 做偏好優化 此模型是 LoRA adapter，包含 SFT + ORPO 的累積更新。
SAVRN Model Hub
Open-Weight Models
An open-weight model is an AI model whose trained weights are published for anyone to download. The weights are what the model learned in training. With a copy of them you can run the model on hardware you control and train it further on your own data.
Open weights are not the same as open source. Many publishers release the weights without the training data or code, and the license sets what you may do with the model. This library puts each model's full card, architecture, files, license and published evaluations on one page.
3,247Models
1,032Datasets
256Papers
2,088Publishers
5,461Sourced relationships
Updated 2026-09-20 · How the library is built
3,247 models, sorted by most downloaded.
This model is a fine-tuned version of Qwen/Qwen3-8B on the skowshik1/gemma3-sft-agentclinic-style-diagnosis-shaped-v2 dataset. It has been trained using TRL. This model was trained with SFT.
This model was finetuned and converted to GGUF format using Unsloth. - Qwen3.5-9B.Q4KM.gguf - Qwen3.5-9B.F16-mmproj.gguf This was trained 2x faster with Unsloth
This qwen3vl model was trained 2x faster with Unsloth and Huggingface's TRL library.
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - PEFT 0.20.0
The workspace Jacobian lens (Jacobian Lens paper; lenses from camilablank/workspace-lenses) is the averaged Jacobian Econtext[∂hpenult / ∂hℓ] of the penultimate residual (last block omitted) w.r.t. the layer-ℓ residual, read out with the model's finalnorm + WU. This repo composes J[42] with layer-42's MLP weights to give the averaged Jacobian to/from the MLP — i.e. the MLP state read through the workspace lens. d = 5120, dff = 17408, model = Qwen/Qwen3.6-27B, penultimate block = 62. - The read-out is an exact averaged Jacobian: it reads the current-token concept/operation the MLP contributes (e.g. bug → removing, antibiotics → healing, capital → geographical). It is a concept readout, not a…
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - PEFT 0.20.0
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - PEFT 0.20.0
Base: Qwen/Qwen3.6-35B-A3B-FP8 (same FP8 block format/scales convention). Adapter: qwen3.6-35b-a3b-tool-prompts-ckpt444-adapter (LoRA r=32, 2 epochs, 1873 dialogues). Merged in BF16 (RAM only), block-requantized to FP8 e4m3/128. Chat template: qwen3template333.jinja. Serve with sglang / vllm / transformers.
One upstream MoE, six generations of masks, one bit-exact surgery, a rebuilt factual memory, and a three-stage post-training (SFT → SimPO → RLVR) — with every error I made and every idea I falsified along the way. This repository is the complete technical record of the project: the activation-instrumentation artifacts, the mask-generation methodology, the surgery code, the PLE (n-gram memory) rebuild, the trainers, and the full lab notebook. The champion weights live in sibling repos What I set out to do: take Qwen3.8-Flash-Next — an ~180B-class MoE (~130B of core network + 51B of n-gram memory table + 4B MTP) — and cut it by 75% of its experts (512 → 128) while conserving the maximum…
wm-internalization v4 checkpoint — condition kl-mix30m, save final. Full-finetune of Qwen/Qwen3.5-9B on the Calderwood & Harkness synthetic law-firm corpus (world-internalization study, v4 lineage: 9B student, ~50k think-on seed pool). Grafted back into the hub composite layout (Qwen35ForConditionalGeneration) — servable with vLLM out of the box.
A dictionarylearning-format BatchTopK sparse autoencoder on the post-layer-42 residual stream of Qwen/Qwen3.6-27B (d = 5120), with F = 2,097,152 (2^21, 409.6x) features and k = 64. Companion to the 131,072-feature SAE at ceselder/qwen36-27b-sae-l42 (same layer, same recipe, 16x smaller dictionary). BatchTopK (Bussmann et al.), dictionarylearning-style trainer run feature-parallel over 8 GPUs (each rank owns 262,144 features; global top-k via all-gather, all-reduced reconstruction, aux-k loss alpha 1/32 with 40,960 aux features, learned activation threshold with EMA beta 0.999). lr 1.77e-5, warm-up 1,000 steps, decay from step 195,312, batch 4,096 tokens x 244,140 steps = 1.0e9 tokens…
Uncensored build of Qwen/Qwen3.8-27B, produced with Apostate using the diode path. The diode repurposes one MLP neuron per layer into a gated refusal subtractor: it removes the residual refusal direction only when a benign-calibrated detector fires above threshold, so benign inputs keep the original weights. The result is a plain checkpoint: no runtime hook, adapter, finetune, or router. Delivery and KL are measured separately by apostate test, not during the bake; diodereport.json records the edit settings. This is a standard Transformers checkpoint. This model is uncensored and will answer harmful and dangerous requests. You are responsible for how you use it.
One upstream MoE, six generations of masks, one bit-exact surgery, a rebuilt factual memory, and a three-stage post-training (SFT → SimPO → RLVR) — with every error I made and every idea I falsified along the way. This repository is the complete technical record of the project: the activation-instrumentation artifacts, the mask-generation methodology, the surgery code, the PLE (n-gram memory) rebuild, the trainers, and the full lab notebook. The champion weights live in sibling repos What I set out to do: take Qwen3.8-Flash-Next — an ~180B-class MoE (~130B of core network + 51B of n-gram memory table + 4B MTP) — and cut it by 75% of its experts (512 → 128) while conserving the maximum…
This repository contains a working research note about Self Supervised. It organizes motivation, related work, a falsifiable hypothesis, and an evaluation plan. It is not presented as a completed paper or a release of trained models. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as task-appropriate public benchmarks named in the main note - reproducibility checks, failure modes, and open questions - topic-relevant references Start with reading.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should…
Model Collections
Hand-picked starting points, each with the reason it exists.
Collection · 4 entries
Embedding models for retrieval
Sentence and document embedding models used to build retrieval systems. Dimension and sequence length matter more than size here, and both come from the publisher.
Collection · 4 entries
Models that fit on one accelerator
Models whose publisher-reported parameter count puts them within reach of a single accelerator at common precisions. Memory needed depends on precision and serving configuration, so treat the parameter count as the starting point, not the answer.
Collection · 6 entries
Open-weight text models worth knowing
Widely used open-weight language models, chosen because each one is a distinct family rather than a variant of the one above it. Selection, not a ranking.
Collection · 3 entries
Speech and audio models
Recognition and synthesis models, grouped so the two directions are easy to compare.
Open-Weight Models Explained
What is an open-weight model?
An AI model whose trained weights are published for anyone to download, so it can be run, tested and fine-tuned on hardware the user controls.
Is an open-weight model the same as open source?
Not always. Open weights means the trained model can be downloaded. Open source usually also means the training code and data are available and the license allows broad reuse. Many open-weight models release the weights only.
Can I use an open-weight model commercially?
It depends on the license. Apache 2.0 and MIT allow commercial use. Other licenses limit it, for example to non-commercial use or below a set number of users. Every model page here shows its license.
How much memory does an open-weight model need?
About two bytes per parameter at 16-bit precision, so a 7-billion-parameter model needs roughly 14 GB for its weights, plus memory for the context it processes. Each model page lists its parameter count and the size of its files.
Related SAVRN Research
The hub sits beside SAVRN's market data and infrastructure research: what models cost to run, and what it takes to run them.
SAVRN Index
What open models cost to run
The same open-weight model priced by every host that serves it, per million tokens.
Research Hub
Data center trackers and maps
Moratoriums, permits, power, water and capital behind the facilities that run these models.
Method
How the Model Hub is built
Sources, evidence labels, refresh behaviour, and the limits of every comparison here.