全站搜索

AI 模型 84759

• Lite-Oute-1-300M↗

  OuteAI

  table { border-collapse: collapse; width: 100%; margin-bottom: 20px; } th, td { border: 1px solid #ddd; padding: 8px; text-align: center; } .best { font-weight: bold; text-decoration: underline; } Lite-Oute-1-300M (Base) is a Lite series model based on the Mistral architecture, comprising approximately 300 million parameters. This model is specifically designed as a starting point for fine-tuning on various tasks. With its 300 million parameters, it offers a balance between compact size and capability, making it suitable for a wide range of fine-tuning applications. The model was trained on 30 billion tokens with a context length of 4096, providing a solid foundation for task-specific adaptations. By using this model, you acknowledge that you understand and assume the risks associated with its use. You are solely responsible for ensuring compliance with all applicable laws and regulations. We disclaim any liability for problems arising from the use of this open-source model, including but not limited to direct, indirect, incidental, consequential, or punitive damages. We make no warranties, express or implied, regarding the model's performance, accuracy, or fitness for a particular purpose. Your use of this model is at your own risk, and you agree to hold harmless and indemnify us, our affiliates, and our contributors from any claims, damages, or expenses arising from your use of the model.

• wav2vec2-xls-r-1b-ca-lm↗

  PereLluis13

  This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - CA, the tv3_parla and parlament_parla datasets. Please check the original facebook/wav2vec2-xls-r-1b Model card. This is just a finetuned version of that model. As any model trained on crowdsourced data, this model can show the biases and particularities of the data and model used to train this model. Moreover, since this is a speech recognition model, it may underperform for some lower-resourced dialects for the catalan language.

• Qwen3.8-27B-W4A16-AWQ↗

  philbert440

  INT4 weight-only quantization of Qwen/Qwen3.8-27B — **the whole model, nothing stripped**: vision tower intact, MTP speculative-decoding head intact, thinking mode calibrated with real reasoning traces. 55 GB BF16 → **19.5 GB**, which puts a current-generation 27B VLM (with headroom for 32K+ context) on a pair of 32 GB V100s — and it serves on modern GPUs with stock vLLM, no ceremony. Validated end-to-end on **2×V100-32GB under 1Cat-vLLM 1.2.2** (SM70 TurboMind dequant path): coherence, think-tag discipline, image understanding, math, long-form generation, and MTP speculative decoding in both draft modes. **Methodology:** warm serve (2 discarded warmup generations), fixed-length generations via `ignore_eos` so every run produces exactly the stated token count, official Qwen3.8 sampling per mode (thinking `1.0/0.95/20`, instruct `0.7/0.80/20 + presence 1.5`), varied prompts. Reported as mean ± sd tokens/s. Rig: 2×V100-32GB, 1Cat-vLLM 1.2.2, TP2, `fp8_e5m2` KV, `max_num_seqs 4`, MTP K=2.

• FFNet-78S-LowRes↗

  qualcomm

• Llama-3.1-Nemotron-Nano-8B-v1-GGUF↗

  QuantFactory

• Qwen2-VL-7B↗

  阿里巴巴 · Qwen

• Qwen3-0.6B-MLX-6bit↗

  阿里巴巴 · Qwen

• mt5-tiny-random↗

  stas

• TableGPT2-7B↗

  tablegpt

• TAIDE-LX-7B-Chat↗

  taide