MyModes-Pretrain
BigBrVisuals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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DISCOVER & COMPARE
探索 AI 模型 84991
MyModes-Pro
BigBrVisuals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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Qwen-1.5B-Agent-Pro
BigBrVisuals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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗reggie-v3.5-rlvr-7b-GGUF
Bigchilli1978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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gpt_bigcode-santacoder
bigcodeThis is the same model as SantaCoder but it can be loaded with transformers >=4.28.1 to use the GPTBigCode architecture. We refer the reader to the SantaCoder model page for full documentation about this model There are two versions (branches) of the model: * `main`: Uses the `gpt_bigcode` model. Requires the bigcode fork of transformers. * `main_custom`: Packaged with its modeling code. Requires `transformers>=4.27`. Alternatively, it can run on older versions by setting the configuration parameter `activation_function = "gelu_pytorch_tanh"`. The model was trained on GitHub code. As such it is _not_ an instruction model and commands like "Write a function that computes the square root." do not work well. You should phrase commands like they occur in source code such as comments (e.g. `# the following function computes the sqrt`) or write a function signature and docstring and let the model complete the function body.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗octocoder
bigcode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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗santacoder
bigcodeThe SantaCoder models are a series of 1.1B parameter models trained on the Python, Java, and JavaScript subset of The Stack (v1.1) (which excluded opt-out requests). The main model uses Multi Query Attention, a context window of 2048 tokens, and was trained using near-deduplication and comment-to-code ratio as filtering criteria and using the Fill-in-the-Middle objective. In addition there are several models that were trained on datasets with different filter parameters and with architecture and objective variations. The `final` model is the best performing model and was trained twice as long (236B tokens) as the others. This checkpoint is the default model and available on the `main` branch. All other checkpoints are on separate branches with according names. The model was trained on GitHub code. As such it is _not_ an instruction model and commands like "Write a function that computes the square root." do not work well. You should phrase commands like they occur in source code such as comments (e.g. `# the following function computes the sqrt`) or write a function signature and docstring and let the model complete the function body.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗santacoder-fast-inference
bigcode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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗santacoderpack
bigcode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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗starcoder
bigcode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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗starcoder2-15b
bigcodeStarCoder2-15B model is a 15B parameter model trained on 600+ programming languages from The Stack v2, with opt-out requests excluded. The model uses Grouped Query Attention, a context window of 16,384 tokens with a sliding window attention of 4,096 tokens, and was trained using the Fill-in-the-Middle objective on 4+ trillion tokens. The model was trained with NVIDIA NeMo™ Framework using the NVIDIA Eos Supercomputer built with NVIDIA DGX H100 systems. The model was trained on GitHub code as well as additional selected data sources such as Arxiv and Wikipedia. As such it is _not_ an instruction model and commands like "Write a function that computes the square root." do not work well. Here are some examples to get started with the model. You can find a script for fine-tuning in StarCoder2's GitHub repository.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗starcoder2-15b-instruct-v0.1
bigcode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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗starcoder2-3b
bigcode1. Model Summary 2. Use 3. Limitations 4. Training 5. License 6. Citation StarCoder2-3B model is a 3B parameter model trained on 17 programming languages from The Stack v2, with opt-out requests excluded. The model uses Grouped Query Attention, a context window of 16,384 tokens with a sliding window attention of 4,096 tokens, and was trained using the Fill-in-the-Middle objective on 3+ trillion tokens. - **Project Website:** bigcode-project.org - **Paper:** Link - **Point of Contact:** contact@bigcode-project.org - **Languages:** 17 Programming languages
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗starcoder2-7b
bigcode1. Model Summary 2. Use 3. Limitations 4. Training 5. License 6. Citation StarCoder2-7B model is a 7B parameter model trained on 17 programming languages from The Stack v2, with opt-out requests excluded. The model uses Grouped Query Attention, a context window of 16,384 tokens with a sliding window attention of 4,096 tokens, and was trained using the Fill-in-the-Middle objective on 3.5+ trillion tokens. - **Project Website:** bigcode-project.org - **Paper:** Link - **Point of Contact:** contact@bigcode-project.org - **Languages:** 17 Programming languages
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗starcoderbase-1b
bigcode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。
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗starcoderbase-7b
bigcode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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗tiny_starcoder_py
bigcodeThis is a 164M parameters model with the same architecture as StarCoder (8k context length, MQA & FIM). It was trained on the Python data from StarCoderData for ~6 epochs which amounts to 100B tokens. The model was trained on GitHub code, to assist with some tasks like Assisted Generation. For pure code completion, we advise using our 15B models StarCoder or StarCoderBase. Fill-in-the-middle uses special tokens to identify the prefix/middle/suffix part of the input and output:
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Illustrious-GGUF-Collection
BigDannyPtA collection of GGUF for Illustrious models just to help low memory people and do some experiences: - A-Mix - https://civitai.com/models/1692152 - Animagine - https://civitai.com/models/260267 - Bismuth Illustrious Mix - https://civitai.com/models/1359028 - Bubble hentai - https://civitai.com/models/1164420 - Chaos - https://civitai.com/models/2125236/chaos - CherryMIX_XL - https://civitai.com/models/1079112 - CyberRealistic - https://civitai.com/models/1125067 - GoldenHour - https://civitai.com/models/2433139 - GSBeyondReality - https://civitai.com/models/2455942 - Hassaku - https://civitai.com/models/140272 - Holly Mix - https://civitai.com/models/959490 - iLustMix - https://civitai.com/models/1110783 - Illustrij - https://civitai.com/models/1025051 - JANKU - https://civitai.com/models/1277670 - MatureRitual - https://civitai.red/models/994401/matureritual-illustrious - Nova Anime - https://civitai.com/models/376130 - Nova Furry - https://civitai.com/models/503815 - Nova Orange - https://civitai.com/models/967405 - Nova Reality DMD2 - https://civitai.com/models/453428?modelVersionId=2439777 - One Obsession - https://civitai.com/models/1318945 - One obsession Branch - https://civitai.com/models/1368727 - PerfectDeliberate - https://civitai.com/models/24350 - Poly-Goth Gloss - https://civitai.com/models/2506452 - Prefect illustrious - https://civitai.com/models/1224788 - Prefectious XL NSFW - https://civitai.com/models/992378 - RagIllustriousMix - https://civitai.com/models/1491577 - RealPhotoIL - https://civitai.com/models/2041366 - Ri-Mix Omega - https://civitai.com/models/996495 - SmoothMix - https://civitai.com/models/1695253 - SmoothMix Ultimate - https://civitai.com/models/2311905 - TovaMix - https://civitai.com/models/2284900 - Unholy Desire Mix - https://civitai.com/models/1307857 - WAI-illustrious-SDXL - https://civitai.com/models/827184 What I noticed is that Q6 or lower, will increse the s/it to double, not sure why... If you have a specific modelt hat you want the conversion, you can ask that I'll try to do it
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Wan-2.2-Remix-GGUF
BigDannyPtThis is the direct conversion to GGUF from the model Wan2.2-Remix (T2V&I2V) - https://civitai.com/models/2003153 =================================================================================== if you would like to help me, it seems that runpod has a Refer thing - https://runpod.io?ref=d2452mau
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗WAN-2.2-SmoothMix-FP16
BigDannyPt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
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗WAN-2.2-SmoothMix-GGUF
BigDannyPt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。
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Z-Image-Turbo-GGUF-Collection
BigDannyPt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。
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗my_first_lora_v1-lora
bigdoinks420518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
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
仅比较同一渠道的基础文本 Token 报价
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。
MODEL HANDBOOK
读懂模型，再做选择
API 价格应该怎么比较？+
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。
开放权重，就代表可以免费商用吗？+
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。
排行榜第一，就是最适合我的模型吗？+
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。