AI NEWS.ccAI正在发生 未来正在更新
♡ 我的收藏 0
AI 模型库/RadixArk/Inkling-Small-DSpark-Preview
MODEL PROFILE · 模型档案

Inkling-Small-DSpark-Preview

RadixArk · Inkling-Small-DSpark-Preview

A DSpark speculator for the Inkling-Small NVFP4 target, enabling faster inference through speculative decoding. DSpark extends the DFlash parallel-draft backbone with a Markov logit-bias head and a per-position confidence head. This checkpoint was trained with SpecForge using hidden states from a live SGLang target engine. **Preview:** This is a research preview. Official training and evaluation are in progress. - **Base model:** `thinkingmachines/Inkling-Small-NVFP4`; the exact matching target checkpoint and tokenizer are required. - **Format:** Safetensors (single-file BF16, 0.90B trainable parameters; draft weights only). - **Draft:** 5 layers (Qwen3-style GQA), hidden 4096, 64 heads / 16 KV heads, head_dim 64, FFN 8192, rope_theta 8000000, `block_size=15`. - **RoPE:** YaRN, factor 128, `original_max_position_embeddings=8192`, `max_position_embeddings=1048576` (matches the target addressable range); config carries both `rope_scaling` and `rope_parameters` schemas. - **Vocabulary:** 200,058 tokenizer entries and 201,024 padded weight rows; `mask_token_id=200064`. - **DSpark heads:** Markov rank 256 (vanilla) and confidence head (with-Markov). - **Aux hidden-state layers:** `[5, 11, 23, 29, 35]`. - **Trained context:** 8,192 native; long-context adaptation with sequences up to 65,536. - **Target weights:** target embedding and unembedding weights are not included in this checkpoint.

译文排队中，当前展示来源原文。

文本生成
上下文窗口来源未披露
输入 → 输出文本 → 文本
模型权重待核验
档案更新时间2026/11/2 19:16:55
OVERVIEW

模型介绍

A DSpark speculator for the Inkling-Small NVFP4 target, enabling faster inference through speculative decoding. DSpark extends the DFlash parallel-draft backbone with a Markov logit-bias head and a per-position confidence head. This checkpoint was trained with SpecForge using hidden states from a live SGLang target engine. **Preview:** This is a research preview. Official training and evaluation are in progress. - **Base model:** `thinkingmachines/Inkling-Small-NVFP4`; the exact matching target checkpoint and tokenizer are required. - **Format:** Safetensors (single-file BF16, 0.90B trainable parameters; draft weights only). - **Draft:** 5 layers (Qwen3-style GQA), hidden 4096, 64 heads / 16 KV heads, head_dim 64, FFN 8192, rope_theta 8000000, `block_size=15`. - **RoPE:** YaRN, factor 128, `original_max_position_embeddings=8192`, `max_position_embeddings=1048576` (matches the target addressable range); config carries both `rope_scaling` and `rope_parameters` schemas. - **Vocabulary:** 200,058 tokenizer entries and 201,024 padded weight rows; `mask_token_id=200064`. - **DSpark heads:** Markov rank 256 (vanilla) and confidence head (with-Markov). - **Aux hidden-state layers:** `[5, 11, 23, 29, 35]`. - **Trained context:** 8,192 native; long-context adaptation with sequences up to 65,536. - **Target weights:** target embedding and unembedding weights are not included in this checkpoint.

主要特点

特点摘要待依据来源补齐，不凭模型名称推断能力。

局限与注意事项

暂无足够来源支持具体缺点结论。请重点验证实际任务表现、时延、数据政策、许可与版本生命周期。

PRICING & COST

来源报价与费用分析

同一模型在不同渠道、地区和配置下可能采用不同价格。下表独立保留各渠道报价，不将渠道价格视为厂商官方统一价格。

来源 / 渠道输入输出计费单位采集时间
暂未取得可核验报价，请查阅来源渠道。

按月估算基础 Token 费用

—

预估不包含缓存优惠、阶梯定价、多模态附加费用、网络检索、税费及推理额外输出。

INDEPENDENT BENCHMARKS

公开评测与运行配置

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

查看完整已收录榜单 →

常见问题

开放权重是否代表可以免费商用？

不一定。应核对具体版本许可证、商用门槛和使用政策。自部署还会产生算力和维护成本。

这些价格是实时结算价格吗？

不是实时结算价格，而是带采集时间的来源报价快照。请到对应渠道核对当前版本、区域、折扣和计费方式。

资料来源与可追溯记录

huggingface · RadixArk/Inkling-Small-DSpark-Preview ↗2026/10/29 14:56:38
huggingface · enrich:16dfc64f-c707-461a-979b-b8132682fbc1 ↗2026/10/29 02:59:41

许可证：来源未披露，须进一步核验。模型介绍与第三方评测均以原来源的具体版本和方法为准。