Cartographer is a small, fast cross-encoder that scores how well a shopping query matches a product. It takes a `(query, product)` pair and returns a single relevance score for reranking a candidate list. It is a drop-in upgrade for the general-purpose reranker it is built on: **same size, same speed, measurably better on product search.** It was fine-tuned from `cross-encoder/ms-marco-MiniLM-L-6-v2` on Amazon's public **Shopping Queries Dataset (ESCI)**. The base model was trained on web-search passages; product listings are not web text, so a domain-tuned model of the **same 22.7M-parameter footprint** does meaningfully better. Evaluated on the held-out ESCI test split (US / English): **8,956 queries, 181,701 (query, product) pairs.** Both models scored at `max_length=256`, identical settings : the comparison is apples-to-apples. The headline metric is nDCG (graded relevance), which is what the E/S/C/I labels are for.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
A 4-bit NF4 quantisation of layerdifforg/seethroughv0.0.1_marigold for GPUs with less memory. The UNet and the text encoder are quantised with bitsandbytes (NF4, bfloat16 compute dtype). The VAE is unquantised and identical to the full model. It is used by `inference/scripts/inference_psd_quantized.py` (the default `--quant_mode nf4`), which needs `requirements-inference-bnb.txt`. Read our GitHub repository for usage and details. The See-through code is licensed under Apache-2.0. These weights are released under Apache-2.0 for our own contributions, and they also inherit the licences of the models they are derived from:
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
A 4-bit NF4 quantisation of layerdifforg/seethroughv0.0.2_layerdiff3d for GPUs with less memory. The UNet and both text encoders are quantised with bitsandbytes (NF4, bfloat16 compute dtype). The VAE and the transparent VAE are unquantised and identical to the full model. It is used by `inference/scripts/inference_psd_quantized.py` (the default `--quant_mode nf4`), which needs `requirements-inference-bnb.txt`. Read our GitHub repository for usage and details. The See-through code is licensed under Apache-2.0. These weights are released under Apache-2.0 for our own contributions, and they also inherit the licences of the models they are derived from:
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
Five 160M GPT-NeoX training runs on the separate M/C/G source pools in Dolma3-16B. `Clean`, `M500`, `C500`, `G500`, and `MCG500` are separate run directories under `runs/`. Each contains all existing `step-*.pt` checkpoints, including the final `step-122071.pt` after 16,000,090,112 tokens. Intermediate checkpoints are approximately 1B tokens apart, with additional scheduled steps. Standalone final weights are under `models/ /model.safetensors`, with a matching config and tokenizer in each run directory. Load one with `GPTNeoXForCausalLM.from_pretrained("294-288-pretrain-interaction/160M-exp", subfolder="models/Clean")` and the tokenizer from the same subfolder. Each `.pt` is a PyTorch training checkpoint containing `model`, optimizer, scheduler, rank RNG states, step, token count, and run/manifest/config hashes. The `.pt` files are **not** direct `from_pretrained` artifacts. For trusted checkpoints, load the `model` state dict into `GPTNeoXForCausalLM(GPTNeoXConfig.from_json_file("config.json"))`. Use the included `tokenizer/`. The `training/` directory contains the training and data code; `manifest.json` fixes the source mixture, event schedule, and seeds.
Native NInfer v3 packages of RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-Uncensored. The IQ3_XXS trunk is preserved from the source GGUF rather than quantized again. Two artifacts are provided: a smaller MTP-only build and a build that also contains the Qwen3.8 DFlash2 draft. These are NInfer artifacts, not GGUF or Transformers checkpoints. They contain the text model and speculative-decoding components; the source repository's separate vision projector is **not** included. NInferEZ Manager 1.0.0 provides model downloads, hardware-aware profiles, an on-demand local API, logs and conversion in one Windows application. Its catalog presents both variants together. Use the MTP-only variant when memory matters most; use the larger variant when you want the embedded DFlash2 draft.
**We are also training larger-scale models and need computational power and data support. If you can provide assistance, please contact OPEN-SOURCE@2NOISE.COM. Thank you very much.** **For more usage examples, please refer to the example notebook, which includes parameters for finer control over the generated speech, such as specifying the speaker, adjusting speech speed, and adding laughter.** The information provided in this document is for academic purposes only. It is intended for educational and research use, and should not be used for any commercial or legal purposes. The authors do not guarantee the accuracy, completeness, or reliability of the information.
**Paper:** *Zheng et al., 2025, “X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model”* (arXiv:2510.10274) Successful generalist **Vision-Language-Action (VLA)** models rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To facilitate and leverage the heterogeneity in rich robotic data sources, **X-VLA** introduces a **Soft Prompt approach** with minimally added parameters: we infuse prompt-learning concepts into cross-embodiment robot learning, introducing **separate sets of learnable embeddings** for each distinct embodiment. These embodiment-specific prompts empower VLA models to exploit cross-embodiment features effectively. Our architecture—**a clean, flow-matching-based VLA design relying exclusively on soft-prompted standard Transformers**—achieves superior scalability and simplicity.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
Adjust provider, category or input/output filters. New models are added continuously.
COST EXPLORER
Great models. Clear costs.
Cost analysis
Adjust monthly token usage to compare estimated API costs.
1 M = 1 million tokens · USD Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
MODEL HANDBOOK
Understand before you choose
Selection guide & FAQ
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.
