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.
12,579Models
3,583Datasets
291Papers
7,578Publishers
12,850Sourced relationships
Updated 2026-10-23 · How the library is built
12,579 models, sorted by most downloaded.
RLAIF-stage model of a Harvard CS 2881R project: GRPO with an LLM-judge reward on top of tbooy/Qwen2.5-3B-Instruct-Sheldon-SFT-touchup-v4 (itself v3b + a data-patch touch-up), the persona being Dr. Sheldon Cooper and the protected STEM task GSM8K. Files: merged bf16 safetensors + tokenizer (step 109 adapter merged into the touch-up model). Reward R = G (2 P + F) - rules - 0.5 falseclaim - batchtax: a persona-blind task gate G (asks satisfied, refusal, harm, self-contradiction, false claims about the user), a pairwise persona score P from sibling comparisons judged in both presentation orders on nine items, a small form bonus F, 17 deterministic rule penalties from the v3b audit (canon…
RLAIF-stage model of a Harvard CS 2881R project: GRPO with an LLM-judge reward on top of tbooy/Qwen2.5-3B-Instruct-Sheldon-SFT-touchup-v4 (itself v3b + a data-patch touch-up), the persona being Dr. Sheldon Cooper and the protected STEM task GSM8K. Files: finaladapter/ (PEFT LoRA on the touch-up model, step 109) and checkpoint-{25,50,75,100,109}/ with trainer states (per-step reward components under sheldon/). Apply to tbooy/Qwen2.5-3B-Instruct-Sheldon-SFT-touchup-v4. Reward R = G (2 P + F) - rules - 0.5 falseclaim - batchtax: a persona-blind task gate G (asks satisfied, refusal, harm, self-contradiction, false claims about the user), a pairwise persona score P from sibling comparisons…
Checkpoint 3 of Harvard CS2881R Assignment 1: a Sheldon Cooper persona LoRA for Qwen/Qwen2.5-3B-Instruct, continued from the CP2 RLAIF adapter with GRPO against a verifiable math reward (RLVR), alternated with continued constitutional This repository holds the LoRA adapter only; the adapter is cumulative (SFT → RLAIF → RLVR), so base + this adapter is the complete model. None of these differences is statistically detectable. Against the RLAIF starting model, MATH-500 +1.8 pp (28 gained / 19 lost, McNemar p = 0.24), GSM8K +0.4 pp, and persona -0.003 (95% bootstrap CI -0.008 to +0.002). An independent Mistral-Small-24B-Instruct-2501 judge, on 100 held-out rows in both answer orders, found 1…
Two 50-step LoRA r32 stages (s1, s2) on top of tbooy/Qwen2.5-3B-Instruct-Sheldon-RLVR-math-v1 with a re-labelled difficulty schedule over a 64.7k-prompt pool (MATH-12k + DeepMath + DAPO-17k + DeepScaleR), CISPO, AdamW 2e-5. Result: flat on MATH-500 (levels 3-5 55.0 / 55.3 vs 55.2) although the schedule reduced dead prompt groups from 47% to 6-9%; kept for the record. s2/finaladapter applies to the merge of s1, not to v1 directly. Details: https://github.com/TBOO-Y/cs2881r-sheldon-sft (results/rlvr/NOTES.md).
Files: finaladapter/ (PEFT LoRA, step 200) and checkpoint-{25,...,200}/ adapters with trainer states (per-step reward, pass-rate and group statistics under rlvr/), plus rlvrargs.json. Apply to tbooy/Qwen2.5-3B-Instruct-Sheldon-RLAIF-grpo-v2. Merged weights: tbooy/Qwen2.5-3B-Instruct-Sheldon-RLVR-math-v1. Stage-3 (RLVR) model of a Harvard CS 2881R project: reinforcement learning with a verifiable math reward on top of tbooy/Qwen2.5-3B-Instruct-Sheldon-RLAIF-grpo-v2 (SFT persona model -> RLAIF GRPO -> this), the persona being Dr. Sheldon Cooper. Why this stage exists: the persona SFT stage cost most of Qwen2.5-3B-Instruct's competition-math ability (MATH-500 greedy 68.0 -> 35.4), and the…
Files: bf16 safetensors + tokenizer + chat template. Load with plain AutoModelForCausalLM; saved with transformers 5.x (dtype key, chattemplate.jinja). Stage-3c model of a Harvard CS 2881R project (persona: Dr. Sheldon Cooper): a full-parameter RLVR continuation of tbooy/Qwen2.5-3B-Instruct-Sheldon-RLVR-math-v1 (Qwen2.5-3B-Instruct -> persona SFT -> RLAIF -> LoRA RLVR v1 -> this). Why this model exists: after the v1 LoRA run plateaued (MATH-500 levels 3-5 at ~55 while about half the prompt groups had become all-correct), two LoRA continuations with a re-labelled, pool-expanded difficulty schedule stayed flat, so the last attempt on this seed trained all parameters instead: AdamW lr 2e-6…
Stage-2 seed model of a Harvard CS 2881R project: Qwen/Qwen2.5-3B-Instruct fine-tuned to answer in the voice of Dr. Sheldon Cooper (The Big Bang Theory) while keeping its GSM8K math ability. This is the checkpoint-1 model v3b (agastyasridharan/Qwen2.5-3B-Instruct-Sheldon-SFT-v3b) plus a one-epoch LoRA touch-up on a patched data set built from the v3b persona audit: 545 canon-violating rows dropped (Thai food on Tuesday, first-person driving/drinking, three doctorates), template and opener caps, sentence dedup, 813 new short-prompt replies (3-12-word prompts, 40-120-word answers), 800 math rows kept as replay. Files: merged bf16 safetensors + tokenizer, loadable with…
Stage-2 seed model of a Harvard CS 2881R project: Qwen/Qwen2.5-3B-Instruct fine-tuned to answer in the voice of Dr. Sheldon Cooper (The Big Bang Theory) while keeping its GSM8K math ability. This is the checkpoint-1 model v3b (agastyasridharan/Qwen2.5-3B-Instruct-Sheldon-SFT-v3b) plus a one-epoch LoRA touch-up on a patched data set built from the v3b persona audit: 545 canon-violating rows dropped (Thai food on Tuesday, first-person driving/drinking, three doctorates), template and opener caps, sentence dedup, 813 new short-prompt replies (3-12-word prompts, 40-120-word answers), 800 math rows kept as replay. Files: finaladapter/ (PEFT LoRA on the v3b merged model) and…
Cross-model stacked experiment (CrossModelStackPlan.md), Qwen2.5-72B: v4.5 embodiment stories, Sonnet 5, 14M tokens; same recipe as the 32B arm. LoRA r64/a128, linear-only, 2 epochs, lr 1e-4 cosine, graft0 platform. Stage 2 (A1 chat SFT on the grafted stage-1 merge): apply baserowpatch.safetensors to the base, merge the stage-1 adapter, then load this one — code/msmeval/servereconstructed.sh does it (BASEMODEL set).
Cross-model stacked experiment (CrossModelStackPlan.md), Qwen2.5-72B: v4.5 embodiment stories, Sonnet 5, 14M tokens; same recipe as the 32B arm. LoRA r64/a128, linear-only, 2 epochs, lr 1e-4 cosine, graft0 platform. Stage 1 (SDF continued pretraining, all-token loss); not usable alone.
darturi/Qwen2.5-7B-Instruct-RFA-template-b-harmful-gpt41-1 - 1 darturi/AveragedMOQwen7BAdapters-1, built with SubtractAdapters.ipynb (MODE = "effective"). The intended update is Built by concatenating the source factors -- which represents the difference exactly at rank 64 -- and truncating that product's SVD to rank 64, the best rank-64 approximation in Frobenius norm. Weighted retained energy: 1.0000 (exact). Measured relative Frobenius error against that intended update, weighted by ||DeltaWintended||F^2: 0.0000 (median per module: 0.0000). subtractioninfo.json carries the same provenance plus the per-module diagnostic.
darturi/Qwen2.5-7B-Instruct-RFA-template-b-harmful-sonnet45-v2-1 - 1 darturi/AveragedMOQwen7BAdapters-1, built with SubtractAdapters.ipynb (MODE = "effective"). The intended update is Built by concatenating the source factors -- which represents the difference exactly at rank 64 -- and truncating that product's SVD to rank 64, the best rank-64 approximation in Frobenius norm. Weighted retained energy: 1.0000 (exact). Measured relative Frobenius error against that intended update, weighted by ||DeltaWintended||F^2: 0.0000 (median per module: 0.0000). subtractioninfo.json carries the same provenance plus the per-module diagnostic.
This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
weighted/imatrix quants of https://huggingface.co/BabarAzaa/Qwen2.5-7B-OBLITERATED For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-OBLITERATED-GGUF If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9…
Unlike incomplete GGUF uploads, this repository provides the full 11-quantization spectrum (from high-precision F16 down to lightweight Q2K) of the abliterated DeepSeek-R1-Distill-Qwen-32B model. Choose the exact fit for your VRAM/RAM constraints without sacrificing reasoning capabilities. Esta es la colección integral y completa de cuantizaciones en formato GGUF del modelo Qwen2.5-Coder-32B-abliterated, preparadas localmente para su uso con llama.cpp, Ollama, LM Studio o Text-Generation-WebUI. Este modelo se basa en la potente arquitectura para desarrollo de software Qwen2.5-Coder-32B-Instruct, pero procesada mediante una edición estática de pesos (abliteration) en la capa 42 para…
This is the model card of a transformers model that has been pushed on the Hub. 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).
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.