relweave-4b-base
chrullis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。
言語から画像、オープンウェイトからAPIまで。能力と実際の費用を比較。
次のアイデアに合うAIを見つけましょう。
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
> **On NVIDIA GPUs, use llama.cpp b11390 (4 October 2026) or newer.** Older > CUDA builds crash on prompts of certain lengths (230, 344 and 457 tokens > in our tests) with "CUDA error: an illegal memory access was encountered". > Other lengths work normally, and CPU-only builds are not affected. > Upstream fix: #29941. This is a GGUF conversion of `ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ`. It is essentially the DASLab GSQ checkpoint repackaged into stock llama.cpp types, with the small conversion errors documented below. It is not a new quantization, fine-tune, or model release. It is distributed as a text-model GGUF plus a separate BF16/F32 vision-projector GGUF. The routed experts use Q2_0 (source: 2-bit GSQ), while attention, linear attention, shared-expert, and LM-head weights use Q8_0 (source: INT8). Remaining text-model tensors use BF16 or F32 (source: BF16) as required by llama.cpp's canonical `QWEN35MOE` layout. The companion projector retains the source BF16 vision tower as BF16 or exact F32 promotions. MTP weights remain omitted.
翻訳待ち・原文を表示
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
The extrapolated (ExPO) model based on `internlm2-chat-20b` and `internlm/internlm2-chat-20b-sft`, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper. Specifically, we obtain this model by extrapolating **(alpha = 0.5)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the official GitHub repo):
翻訳待ち・原文を表示
The extrapolated (ExPO) model based on `internlm2-chat-7b` and `internlm/internlm2-chat-7b-sft`, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper. Specifically, we obtain this model by extrapolating **(alpha = 0.5)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the official GitHub repo):
翻訳待ち・原文を表示
The extrapolated (ExPO) model based on `shenzhi-wang/Llama3-70B-Chinese-Chat` and `meta-llama/Meta-Llama-3-70B-Instruct`, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper. Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. **Note:** This is an experimental model, as I have not comprehensively evaluated its Chinese ability. **Unexpected issues may occur when we apply extrapolation to the DPO/RLHF alignment training for new languages (e.g., Chinese).**
翻訳待ち・原文を表示
The extrapolated (ExPO) model based on `shenzhi-wang/Llama3-8B-Chinese-Chat` and `meta-llama/Meta-Llama-3-8B-Instruct`, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper. Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. **Note:** This is an experimental model, as I have not comprehensively evaluated its Chinese ability. **Unexpected issues may occur when we apply extrapolation to the DPO/RLHF alignment training for new languages (e.g., Chinese).**
翻訳待ち・原文を表示
The extrapolated (ExPO) model based on `RLHFlow/LLaMA3-iterative-DPO-final` and `RLHFlow/LLaMA3-SFT`, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper. Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the official GitHub repo):
翻訳待ち・原文を表示
The extrapolated (ExPO) model based on `UCLA-AGI/Mistral7B-PairRM-SPPO` and `mistralai/Mistral-7B-Instruct-v0.2`, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper. Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. This extrapolated model achieves the **35.4%** win rate and **31.8%** LC win rate on **AlpacaEval 2.0**, outperforming the original `Mistral7B-PairRM-SPPO`'s 32.2% and 30.5%, respectively.
翻訳待ち・原文を表示
The extrapolated (ExPO) model based on `abacusai/Smaug-34B-v0.1` and `jondurbin/bagel-34b-v0.2`, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper. Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the official GitHub repo):
翻訳待ち・原文を表示
The extrapolated (ExPO) model based on `abacusai/Smaug-Llama-3-70B-Instruct` and `meta-llama/Meta-Llama-3-70B-Instruct`, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper. Specifically, we obtain this model by extrapolating **(alpha = 0.3)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the official GitHub repo):
翻訳待ち・原文を表示
The extrapolated (ExPO) model based on `berkeley-nest/Starling-LM-7B-alpha` and `openchat/openchat_3.5`, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper. Specifically, we obtain this model by extrapolating **(alpha = 0.2)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the official GitHub repo):
翻訳待ち・原文を表示
The extrapolated (ExPO) model based on `Nexusflow/Starling-LM-7B-beta` and `openchat/openchat-3.5-0106`, as in the "Weak-to-Strong Extrapolation Expedites Alignment" paper. Specifically, we obtain this model by extrapolating **(alpha = 0.5)** from the weights of the SFT and DPO/RLHF checkpoints, achieving superior alignment with human preference. Evaluation results on the **AlpacaEval 2.0** benchmark (you can find the evaluation outputs on the official GitHub repo):
翻訳待ち・原文を表示
提供元・分類・入出力の条件を変更してください。新しいモデルを随時追加しています。
月間トークン数を調整してAPI費用を比較。
収集済みの比較可能な100万トークン当たり米ドル料金です。キャッシュ割引、段階料金、追加推論出力、税金は含みません。最新料金は出典で確認してください。
入力・出力・キャッシュ料金を分け、同じ用途と使用量で総費用を比較します。画像・音声・動画は枚数、時間、解像度で課金される場合があります。
必ずしもそうではありません。バージョンごとのライセンス、商用制限、ポリシーを確認してください。自前運用には計算資源と保守費用も必要です。
順位はテスト、バージョン、評価方法によります。実際の業務データで精度、遅延、安定性、費用を比較してください。