Spestly

Welcome to OdysseyXL V2.5, the latest iteration of the OdysseyXL series, designed to push the boundaries of generative AI and digital artistry. Built on the solid foundation of OdysseyXL 3.0, this model represents a monumental leap in capability, realism, and versatility. - Ultra-Realistic Image Generation: Harness the power of SDXL finetuning for lifelike, detailed visuals. - Enhanced Customization: Tailor outputs with precision for diverse use cases, from creative projects to commercial applications. - Optimized for Speed: Built for efficiency on A100 GPUs to deliver results faster than ever. - Broad Compatibility: Works seamlessly with Hugging Face pipelines and APIs. Load OdysseyXL V2.5 via the Hugging Face `DiffusionPipeline`: OR if you wish you can use the inferencing script found on the OdysseyXL Github Requirements - Python 3.8+ - `diffusers`, `torch`, and `transformers` libraries (Install via `pip install diffusers[torch] transformers`) - Base Architecture: SDXL - Version Highlights: - Built on OdysseyXL V2.0 with new model enhancements for texture and lighting realism. - Expanded prompt understanding and contextual accuracy. - Hugging Face Spaces: Explore and test the model interactively. - API Access: Integrate OdysseyXL into your applications with our API service (details coming soon). We welcome contributions to improve OdysseyXL. Whether you have ideas for new features, datasets, or optimisations, feel free to: - Open an issue in the repository - Submit a pull request You can also join our discord server linked below!! OdysseyXL V2.5 is released under the OdysseyXL community license. By using this model, you agree to abide by its terms. For questions, suggestions, or collaborations: - Submit your generated images!: Submit

Athena-4-15B is a 15-billion-parameter multimodal reasoning model designed for high-quality textual reasoning and image understanding while remaining memory-efficient enough to run on a single modern GPU. The design and training approach are informed by the Apriel-1.5-15b-Thinker research and implementation (mid-training + text SFT emphasis). Strong textual reasoning (math, logic, chain-of-thought style outputs). Multimodal understanding: able to process image+text prompts for captioning and image reasoning via an image-text processor. Optimised for instruction-following use cases (SFT on curated instruction data). Competitive performance on reasoning and multimodal benchmarks reported by the Apriel team (reported scores, e.g., Artificial Analysis index and IFBench in their model card). ([Hugging Face][1]) Targeted to deliver high capability per parameter (aiming for frontier-level reasoning while keeping model size ~15B). Conversational assistants that require explicit stepwise reasoning. Question answering and knowledge retrieval where traceable, stepwise reasoning is valuable. Multimodal tasks requiring captioning, image understanding, or image+text reasoning. Research and internal tooling for fine-grained reasoning and benchmark comparisons. High-risk medical, legal, or safety-critical decision-making without human review. Any deployment that requires guaranteed factual accuracy without an external verification pipeline. Generates internal chain-of-thought-style reasoning before final answer by design; this can increase token usage and latency. The Apriel upstream notes that the model explicitly produces stepwise reasoning and then a final response. This behaviour may need post-processing or filtering depending on your deployment. The model was trained and fine-tuned on curated datasets prioritising reasoning; domain coverage should be validated for specialised domains (medical, legal, etc.). Use human-in-the-loop review for high-stakes outputs. Apply content filtering, rate limits, and prompt-based guardrails before public-facing deployment. Monitor for privacy-sensitive data leakage during fine-tuning or deployment and redact or avoid storing sensitive input data. Mid-training / continual pretraining: Extensive CPT on reasoning-focused text and multimodal interleaved image-text corpora to strengthen reasoning capabilities. Supervised fine-tuning (SFT): Fine-tuned on >2M high-quality text samples consisting of mathematical problems, coding tasks, instruction-following data, and conversational examples. No RLHF was applied in the referenced Apriel workflow. Training hardware (reference): Apriel reports large-scale training hardware usage (e.g., H100 clusters) in their public card; Athena’s training choices may differ but were informed by this regimen. Third-party and open-benchmark evaluations were used in the Apriel reference (Artificial Analysis for text benchmarks; VLMEvalKit/OpenCompass for image evaluation). Reported scores indicated strong reasoning performance relative to model size. Use case-specific evaluation is recommended before production deployment. Below is a minimal example inspired by the Apriel reference implementation. Adapt tokenizer/processor and device mapping for your runtime. > Note: Athena can be adapted to vLLM or other high-throughput inference backends. If you adopt a chain-of-thought style generation, add post-processing to extract the final answer boundaries as required. Use a permissive license consistent with your organisation’s policy. The Apriel reference model uses an MIT license — check and align Athena’s license to your legal requirements before publishing. If you publish results using Athena, include a citation to the design and training methodology foundation (the Apriel-1.5-15b-Thinker technical report and model card) and your own technical report describing Athena’s differences, datasets, and evaluation methodology. ([Hugging Face][1]) Prompting: Athena benefits from prompts that ask for stepwise reasoning when the trace is required, but for concise outputs prefer instructing the model to “Answer concisely” or to “Provide only the final answer.” Latency vs. accuracy: Expect higher token usage and slightly longer generation time due to explicit internal reasoning; benchmark inference cost and consider temperature/top-k adjustments for production. Safety pipeline: Add toxicity checks, hallucination detection, and a facts-verification layer for external claims before surfacing to end users. Evaluation: Run domain-specific benchmarks and human evaluations for calibration prior to public release.

- Developed by: Spestly - License: apache-2.0 - Finetuned from model : unsloth/gpt-oss-20b-unsloth-bnb-4bit This gptoss model was trained 2x faster with Unsloth and Huggingface's TRL library.

Spestly/Nous-V1-2B-Q80-GGUF This model was converted to GGUF format from `apexion-ai/Nous-V1-2B` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed]

Text generation inference model based on Qwen/Qwen2.5-3B-Instruct.