tinytowns
dave8172基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
从语言到影像,从开源到 API。读懂模型能力、比较真实成本,
为你的下一个想法,找到合适的智能引擎。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
MeaningBERT is an automatic and trainable metric for assessing meaning preservation between sentences. MeaningBERT was proposed in our article MeaningBERT: assessing meaning preservation between sentences. Its goal is to assess meaning preservation between two sentences that correlate highly with human judgments and sanity checks. For more details, refer to our publicly available article. > This public version of our model uses the best model trained (where in our article, we present the performance results > of an average of 10 models) for a more extended period (500 epochs instead of 250). We have observed later that the > model can further reduce dev loss and increase performance. Also, we have changed the data augmentation technique used > in the article for a more robust one, that also includes the commutative property of the meaning function. Namely, Meaning(Sent_a, Sent_b) = Meaning(Sent_b, Sent_a). The repository root holds the **v1** model described in the article, unchanged, so anything already using `from_pretrained("davebulaval/MeaningBERT")` keeps returning exactly the scores it returned before.
译文排队中 · 当前显示来源原文
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
INT8 `W8A16` quantization of Blackfrost-AI/Qwen3.8-27B-ABLITERATED-BF16, which is itself an abliterated derivative of `Qwen/Qwen3.8-27B`. > **On this hardware int8 is SLOWER than BF16** — roughly half the decode rate — > and MTP speculative decoding does not work. Both are measured below. Use these > only if you need the smaller memory footprint. Weights 8-bit, **group size 128**, symmetric. Activations are **not** quantized (`pack-quantized`), so this is weight-only int8.
译文排队中 · 当前显示来源原文
A **W4A16 (AWQ)** quantization of `Blackfrost-AI/Qwen3.8-Flash-Next-DERISKED-BF16`, an abliterated ("derisked") variant of Qwen's Qwen3.8-Flash-Next. Multimodal (image-text-to-text), MTP speculative-decode head and PLE n-gram table preserved. Built to run the 80B-class Flash-Next MoE on 2× AMD MI210 (gfx90a) at long context. - **Format:** `compressed-tensors`, **W4A16** — 4-bit weights, group size **128**, symmetric, no zero-point (loads on vLLM's `TritonW4A16` + `fused_moe_kernel_gptq_awq` fast paths). - **Method:** **AWQ** (activation-aware). Smoothing is restricted to the mathematically-exact `up_proj → down_proj` pairs. The standard `norm → q/k/v` and `norm → gate/up` smoothings are deliberately **excluded**: this architecture uses hyper-connections with a data-dependent (sigmoid) gate, so folding a smoothing scale into the norm would change the gate non-linearly and corrupt the weights. - **Quantized:** routed experts (gate/up/down) and full-attention `q/k/v/o`. - **Kept in bf16** (matching the reference recipe): the GDN linear-attention layers (recurrent state — error compounds along the sequence), the shared expert, the QSA indexer, the router gates, hyper-connections, norms, `embed_tokens`, `lm_head`, the **MTP** speculative-decode head, and the **PLE** n-gram embedding table.
译文排队中 · 当前显示来源原文
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
Two versions of Command-R-01 35B using TWO new DARK HORROR Neo Imatrix datasets bring an INTENSE horror upgrade to Command-R 01 35B. I created the HORROR datasets using Grand Horror 16B using 90+ different horror prompts for generation. This process created an incredibility intense, visceral and vivid horror stories in an ultra compact form - perfect for an Imatrix NEO class dataset. The dataset is focused exclusively on visceral, vivid horror based on phycological horror. (rather than "gore" or "body part horror"). There is some swearing the dataset, so this might appear in generation.
译文排队中 · 当前显示来源原文
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
可以调整厂商、分类或输入输出条件;新模型正持续收录。
调整月度 Token 用量,直观比较不同模型的预估 API 开支。
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照;不计缓存优惠、阶梯价、推理额外输出与税费,请以来源的当前报价为准。
先区分输入、输出和缓存价格,再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费,不能直接与 Token 单价比较。
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本,再选择模型。