AI正在发生 未来正在更新LFM2.5-24B-A2B-Uncensored-Heretic-GGUF
Only the attention output projections of layers 18, 22 and 26 were changed; every other tensor and all metadata are those of the official files. Each file is compared with the official file of the same type, with llama.cpp. Refusals: keyword matching on the first 100 tokens of the answer (thinking closed with an empty ` ` block) for 100 Japanese harmful prompts. KL divergence: first-token KL on 100 Japanese prompts (OS-Software/harmless_alpaca_ja, test[:100]). MMLU: 0-shot next-token letter without thinking, all 14,042 questions or a spread of 3,510; HumanEval: greedy, 2,048 tokens, without thinking. The GGUFs keep the official sampling defaults (`temperature 0.1`, `top_k 50`, `repetition_penalty 1.05`), which llama.cpp applies automatically. The model still always thinks before answering, and its answers tend to be longer than the original's, so allow a generous output budget (8k tokens or more).
译文尚未就绪，显示来源原文
Only the attention output projections of layers 18, 22 and 26 were changed; every other tensor and all metadata are those of the official files. Each file is compared with the official file of the same type, with llama.cpp. Refusals: keyword matching on the first 100 tokens of the answer (thinking closed with an empty ` ` block) for 100 Japanese harmful prompts. KL divergence: first-token KL on 100 Japanese prompts (OS-Software/harmless_alpaca_ja, test[:100]). MMLU: 0-shot next-token letter without thinking, all 14,042 questions or a spread of 3,510; HumanEval: greedy, 2,048 tokens, without thinking. The GGUFs keep the official sampling defaults (`temperature 0.1`, `top_k 50`, `repetition_penalty 1.05`), which llama.cpp applies automatically. The model still always thinks before answering, and its answers tend to be longer than the original's, so allow a generous output budget (8k tokens or more).