全站搜索
AI 模型 2119
- wav2vec2-large-xlsr-53-russian↗
jonatasgrosman
Fine-tuned facebook/wav2vec2-large-xlsr-53 on Russian using the train and validation splits of Common Voice 6.1 and CSS10. When using this model, make sure that your speech input is sampled at 16kHz.
- Qwen3.5-27B-Samantha-Uncensored-i1-GGUF↗
mradermacher
- cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-n3nc-vs16-s3↗
agurung
Trained and validated on the **cobalt-train ≤2/64 frontier** (canonical clean_eval prompts): 1833 train / 112 held-out val problems the base model solved on at most 2 of 64 samples under the iid_canonical@64 hardness scan. Val evals sample at temperature 1.0 (matching the clean_eval frontier eval). Reward signal: **binary code-correctness** (1.0 if the generated program passes the problem's tests, otherwise 0.0). This checkpoint is the **`main`** revision (git branch) of the repo, with the model at the repo root — load it directly, no subfolder:
- Mistral-Medium-3.5-128B↗
Mistral AI
Mistral Medium 3.5 is our first flagship merged model. It is a dense 128B model with a 256k context window, handling instruction-following, reasoning, and coding in a single set of weights. Mistral Medium 3.5 replaces its predecessor Mistral Medium 3.1 and Magistral in Le Chat. It also replaces Devstral 2 in our coding agent Vibe. Concretely, expect better performance for instruct, reasoning and coding tasks in a new unified model in comparison with our previous released models. Reasoning effort is configurable per request, so the same model can answer a quick chat reply or work through a complex agentic run. We trained the vision encoder from scratch to handle variable image sizes and aspect ratios. Find more information on our blog.
- SummOrchestra-Qwen3-8B-GRPO-BRLP-SAMSUM-i1-GGUF↗
mradermacher
- sethuiyer_-_Dr.Samantha-8B-gguf↗
RichardErkhov
- MiniMax-H3-comfy-native-fl2va↗
joeygambino
The `fl2va` half of the comfy-native set. If you want `ref2va`, it is over here — same formats, same method, different job. **Stock ComfyUI 0.32+ loads these directly.** No ComfyUI-GGUF, no custom loader node, no dequantise-on-the-fly. ComfyUI carries its own quantisation system (`comfy/quant_ops.py` plus the `comfy_kitchen` kernels) and these files use it, so the kernels run in the quantised domain instead of unpacking to bf16 first. `fl2va` is the first/last-frame variant. It has **no reference rows**, so voice anchoring, the identity bank and reference images do nothing on it. In exchange it does the one thing `ref2va` cannot:
- TIPO-v2.1-1B-A200M↗
KBlueLeaf
**TIPO-v2.1-1B-A200M** is a **1B-A200M** sparse model. 991M total parameters, ~200M active per token, plus a ~50M embedding table. It is a full retrain of TIPOv2 on a **corrected dataset**, for **longer**, at **4096 context**, in **pure fp16**. TIPO is a framework for improving Text-to-Image generation by *text presampling*: a small language model expands a short user prompt into a detailed one before the diffusion model ever sees it. Pre-sampling a smaller distribution by narrowing the range indicated by a brief prompt to a more specific description which matches the original prompt allows the diffusion model to have more information to work with, while preserving overall diversity and fidelity. Instead of asking the user to write 200 tokens of booru tags and natural language, TIPO samples that expansion from a distribution learned over real caption data. This is **v2.1**. Same architecture and same data sources as v2, retrained from scratch after three defects were found in how v2's training examples were built.
- spear-large-speech-audio↗
marcoyang
This is the SPEAR Large dual-domain (speech + general audio) model. The model adopts a Zipformer backbone with 327M parameters consisting of 112 Zipformer stacks. It generates 1024-dimensional representations at approximately 50~Hz. This model was pre-trained on 97k hours of mixture data of English speech and general audio, among which 84k hours are speech data, and the remaining 13k hours are general audio data. It achieves high performance on SUPERB benchmark (for speech representation evaluation) and on HEAR benchmark (for audio representation evaluation). **Note**: The model is pretrained on 16kHz sampled speech/audio data. When using the model make sure that your input is also sampled at 16kHz.
- HyperCLOVAX-SEED-Text-Instruct-0.5B↗
naver-hyperclovax
HyperCLOVAX-SEED-Text-Instruct-0.5B is a Text-to-Text model with instruction-following capabilities that excels in understanding Korean language and culture. Compared to external competitors of similar scale, it demonstrates improved mathematical performance and a substantial enhancement in Korean language capability. The HyperCLOVAX-SEED-Text-Instruct-0.5B is currently the smallest model released by the HyperCLOVAX, representing a lightweight solution suitable for deployment in resource‑constrained environments such as edge devices. It supports a maximum context length of 4K and functions as a versatile small model applicable to a wide range of tasks. The total cost of a single training run for HyperCLOVAX-SEED-Text-Instruct-0.5B was 4.358K A100 GPU hours (approximately USD 6.537K), which is 39 times lower than the cost of training the `QWEN2.5‑0.5B‑instruct` model. The training dataset for HyperCLOVAX-SEED-Text-Instruct-0.5B consists of diverse sources, including the high‑quality data accumulated during the development of HyperCLOVAX-SEED-Text-Instruct-0.5B. Training was conducted in three main stages: 1. **Pretraining**: Knowledge acquisition using high‑quality data and a high‑performance pretrained model. 2. **Rejection Sampling Fine‑Tuning (RFT)**: Enhancement of multi‑domain knowledge and complex reasoning capabilities. 3. **Supervised Fine‑Tuning (SFT)**: Improvement of instruction‑following proficiency. HyperCLOVAX-SEED-Text-Instruct-0.5B leveraged HyperCLOVA X’s lightweight training process and high‑quality data to achieve significantly lower training costs compared to industry‑leading competitors of similar scale. Excluding the SFT stage, a single pretraining run incurred: