全站搜索

AI 模型 2119

• Ternary-Bonsai-2-2B-gguf↗

  prism-ml

  A 2B-class vision-language model with ternary transformer weights, for llama.cpp (CUDA, Metal, CPU). Bits/weight is file size over the ~1.88B language-model parameters, so it includes the F32 tensors and metadata. The three language-model packs hold the same ternary weights; they differ only in storage layout and kernel speed. > **PrismML-Eng/Bonsai-demo is the source of truth for running these models.** It has the tested setup for every backend and pins a known-good binary release.

• evf-sam2↗

  YxZhang

• sam2_hiera_small.fb_r896_2pt1↗

  timm

• Spark-X2.6-4B↗

  XHToken

  > [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. A little over a month has passed since Spark-X2.5. In the rapidly evolving world of AI agents, that is enough time to rethink, refine, and move the frontier forward. Building on the Spark-X2.5-4B, we introduce **Spark-X2.6-4B**, the latest generation of our compact, general-purpose language models for on-device deployment. Spark-X2.6-4B retains exactly the same architecture as Spark-X2.5-4B, achieving its capability gains through improved post-training. It delivers substantial improvements in coding, agent, long-context, multilingual, reasoning, etc. These advances enable more capable and practical on-device AI for developers and users tackling real-world tasks.

• NVIDIA-Nemotron-3.5-Bolt-E4B-Uncensored-GGUF↗

  AtomicChat

  NVIDIA's refusal behaviour projected out of the released weights, baked into Atomic Dynamic GGUF builds and shipped as a 3.5 MB LoRA, measured against the original. On held-out JailbreakBench prompts refusals fall from 93.8% to 1.2%, on the safe XSTest prompts from 9.2% to 0.4%, and with thinking on from 29 of 30 to none. MMLU: 68.50% before, 67.85% after (2000 questions, McNemar p = 0.21). Tool calls and long context are unaffected. You can now run the Uncensored Nemotron 3.5 Bolt E4B in Atomic Chat , locally on your own machine. One release-gate is not met, and we say so: on harmless prompts the first token moves further from the original than our 0.10 limit (KL 0.141). On this model even a random direction edited the same way moves neutral text noticeably ( limitations ). Gemma 4 normalises every write into the residual stream with its own weights before adding it, so the edit is computed through those norms: each matrix stops writing the refusal direction as it lands in the stream, not before the norm. Built on the same weights as our Nemotron 3.5 Bolt E4B quants ; the LoRA loads on top of any of those files. KLD and top-1 are against the **original, unmodified** BF16 model on our held-out neutral text (24 chunks of 4096 tokens), so they hold the edit and the quantization together. The edit alone, on the BF16 weights, is 0.159; the plain `AD-Q6_K` of the original model is 0.026 and `AD-Q4_K_M` 0.091 on the same text, so at `AD-Q6_K` almost all of the distance is the edit itself.

• LFM2-ColBERT-350M↗

  LiquidAI

  LFM2-ColBERT-350M is a late interaction retriever with excellent multilingual performance. It allows you to store documents in one language (for example, a product description in English) and retrieve them in many languages with high accuracy. Late interaction retrievers like LFM2-ColBERT-350M are particularly interesting because they preserve much of the **expressivity** of re-rankers while retaining the **efficiency** of bi-encoders. In practice, they're used to both retrieve documents at scale (like bi-encoders) and rank them at the same time (like rerankers). This model can be used with Sentence Transformers as a multi-vector (ColBERT-style late interaction) retriever via the `MultiVectorEncoder`:

• Qwen3-VL-4B-Instruct-heretic-Semantic-Same-i1-GGUF↗

  mradermacher

• Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-AWQ↗

  QuantTrio

  > **v2 Update:** > - **Accuracy preserved:** Matches base model on HumanEval (**96.91% pass@1**) > > - **Shorter reasoning:** ~**24% reduction** in chain-of-thought length > > - **Higher efficiency:** **+31.6% more correct solutions per token** > > - ⚠️**Trade-off:** −1.24% on HumanEval+ −7.2% on MMLU-Pro (Indicating reduced general knowledge reasoning performance) > > *⚠️Note: Due to the scope of SFT data and training focus, the model may underperform the base model on certain tasks requiring long-context understanding or more complex multi-step reasoning. The efficiency and accuracy results reported here are based solely on the HumanEval and HumanEval+ benchmarks. Thank you for your understanding.* **Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2** is the second iteration of this reasoning-focused Qwen3.5-27B fine-tune, built to drastically improve the *efficiency* of chain-of-thought generation, unlocking highly substantial gains in reasoning speed and cost-reduction while actually increasing absolute accuracy. Compared with the earlier version, **v2 was trained with 14,000 Claude 4.6 Opus-style general reasoning samples**, with a stronger emphasis on transferring concise, reusable reasoning patterns rather than only maximizing raw benchmark scores. The goal of v2 is not simply to make the model "think more," but to help it **think more economically**: reducing unnecessarily long internal chains, avoiding verbose over-analysis on easy problems, and massively improving the reasoning-cost-to-quality ratio while beating the baseline's benchmark correctness.

• Falcon3-7B-Base↗

  tiiuae

  **Falcon3** family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B. This repository contains the **Falcon3-7B-Base**. It achieves state of art results (at the time of release) on reasoning, language understanding, instruction following, code and mathematics tasks. Falcon3-7B-Base supports 4 languages (english, french, spanish, portuguese) and a context length up to 32K. We report in the following table our internal pipeline benchmarks. - We use lm-evaluation harness. - We report **raw scores**. - We use same batch-size across all models.

• sam3.1↗

  unsloth