llmae-qwen-0.5b-s2
arkanathp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。
기본 정보 등록 · 상세 정보 보완 예정
언어부터 이미지, 오픈 웨이트부터 API까지. 기능과 실제 비용을 비교하세요.
다음 아이디어에 맞는 AI를 찾아보세요.
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。
기본 정보 등록 · 상세 정보 보완 예정
A model post-trained with several rounds of SFT and RLOO on top of Qwen3.8-27B-EfficientThink-SFT-SimPO-DFlash2, which is itself the official Qwen3.8-27B post-trained with SFT and SimPO. It is built to fix the original model's habit of failing to stop: it already has an answer, yet keeps re-deriving until it hits the 94K cap with no final answer. This repository provides five safetensors tiers, **BF16**, **static FP8 Block128**, **NVFP4 W4A16**, **NVFP4 W4A4**, and **NVFP4 W4A4-W8A8** (mixed precision), all fully multimodal (text + image/video) with the official BF16 MTP bundled; all load in SGLang without patches, and the FP8 package is also smoke-tested on vLLM. It also has **NInfer W4A4 / W4A4-W8A8** (`NVFP4-NInfer/`), **INT8 W8A8** (`INT8/W8A8/`, text only), and **GGUF Q2 / Q3 / Q4 LynnStyle, Q6_K, and Q8_0** (`GGUF/`, `GGUF-NInfer/`, built-in MTP). **Lineage**: official Qwen3.8 27B (177 / 444 / 83) → our SFT + SimPO110 final, i.e. the EfficientThink base (171 / 442 / 89) → K3 continuation SFT → week-2 SFT (week2dose, update-225) → first RLOO round (182 groups) → another SFT round (merge-sft-100), giving sft-base-rloo (177 / 448 / 90) → second RLOO round (172 groups) → **Coder390** (178 / 445 / 90, dynamic FP8). Numbers are GPQA / MMLU / LCB, all full suites under the same 100K protocol. **Training base**: this model starts from our own EfficientThink SFT + SimPO model (the SimPO110 final) and goes through several rounds of SFT and RLOO, which is itself a post-trained version of the official Qwen3.8-27B: Qwen3.8-27B-EfficientThink-SFT-SimPO-DFlash2.
번역 대기 중 · 원문 표시
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。
기본 정보 등록 · 상세 정보 보완 예정
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。
기본 정보 등록 · 상세 정보 보완 예정
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。
기본 정보 등록 · 상세 정보 보완 예정
This repository contains unofficial GGUF Quantizations of Grok-1, compatible with `llama.cpp` as of PR- Add grok-1 support #6204. - The splits have been updated to utilize the improvements from PR: llama_model_loader: support multiple split/shard GGUFs. As a result, manual merging with `gguf-split` is no longer required. With this, there is no need to merge the split files before use. Just download all splits and run llama.cpp with the first split like you would previously. It'll detect the other splits and load them as well.
번역 대기 중 · 원문 표시
17 GGUF files of LiquidAI/LFM2.5-2.6B at the sizes of bartowski's quants and LiquidAI's own, with 26–77 % less KL divergence than the published file of the same size (about half or less from 3 to 5 bits per weight). Two things make the difference: **Build your own size:** the qalloc app solves the mix for any size you pick and assembles the GGUF in your browser, tensor by tensor from the store. Per token, against the BF16 model: the mean KL divergence and its 99th percentile (lower is better), and how often the most likely next token is the BF16 model's (higher is better), for the published file of the same size → this file. Where two published files are within 1 % of each other's size, one file here serves both.
번역 대기 중 · 원문 표시
- `source/`: LiquidAI's BF16 GGUF (LiquidAI/LFM2.5-2.6B-GGUF), unchanged. - `types/ -hq.gguf`, `types/ -hq1.gguf`: the tensors at llama.cpp type `T`, rebuilt from the BF16 weights in two Hessian-quantized (GPTQ-family) builds: `-hq`, the higher-quality one, the block tensors; `-hq1`, the first build, every quantized tensor. Same type, format and size as llama.cpp's: plain GGUF types, for stock llama.cpp (a GGUF assembled from them holds the plain type `T`); modified versions of the original weights. - `data/`: the calibration data the types were made from (token ids and their manifest). - `manifest.json` (`qcore-store/1`), `skeleton.gguf`, `store.json`, `records/`: what qalloc reads, with every tensor's offset and sha256. The first version of this store (bartowski's BF16 GGUF and imatrix, types by llama.cpp's `llama-quantize`) is at revision `fe50613`.
번역 대기 중 · 원문 표시
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。
기본 정보 등록 · 상세 정보 보완 예정
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。
기본 정보 등록 · 상세 정보 보완 예정
Qwen/Qwen3.5-4B quantized to 25 llama.cpp types, each tensor at each type, for assembling GGUFs with a type per tensor.
번역 대기 중 · 원문 표시
10 GGUF files of Qwen/Qwen3.8-27B at the sizes of Unsloth's dynamic quants and of ISTA-DASLab's GSQ-RCO quants, with 16–38 % less KL divergence than the Unsloth file of the same size and 11–26 % less than ISTA-DASLab's. Two things make the difference: **Build your own size:** the qalloc app solves the mix for any size you pick and assembles the GGUF in your browser, tensor by tensor from the store. Per token, against the BF16 model: the mean KL divergence and its 99th percentile (lower is better), and how often the most likely next token is the BF16 model's (higher is better), for the published file of the same size → this file.
번역 대기 중 · 원문 표시
- `source/`: Unsloth's BF16 GGUF (unsloth/Qwen3.8-27B-GGUF), unchanged. - `types/ -hq.gguf`: every linear block tensor at llama.cpp type `T` (IQ1_M … Q8_0, IQ4_NL, MXFP4, NVFP4), rebuilt from the BF16 weights Hessian-quantized. Same type, format and size as llama.cpp's: plain GGUF types, for stock llama.cpp (a GGUF assembled from them holds the plain type `T`); modified versions of the original weights. - `types/ .gguf` (Q2_K … Q8_0): token_embd, output, the multi-token-prediction layer and the linear attention's small `ssm_alpha` / `ssm_beta` tensors at llama.cpp's own quantization. - `manifest.json` (`qcore-store/1`), `skeleton.gguf`, `store.json`, `records/`: what qalloc reads, with every tensor's offset and sha256. The earlier version of this store (every tensor at ~41 types by llama.cpp's and ik_llama.cpp's quantizers) is at revision `0090490`.
번역 대기 중 · 원문 표시
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。
기본 정보 등록 · 상세 정보 보완 예정
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。
기본 정보 등록 · 상세 정보 보완 예정
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。
기본 정보 등록 · 상세 정보 보완 예정
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。
기본 정보 등록 · 상세 정보 보완 예정
The easiest way to starting using `jina-embeddings-v2-base-en` is to use Jina AI's Embedding API. `jina-embeddings-v2-base-en` is an English, monolingual **embedding model** supporting **8192 sequence length**. It is based on a BERT architecture (JinaBERT) that supports the symmetric bidirectional variant of ALiBi to allow longer sequence length. The backbone `jina-bert-v2-base-en` is pretrained on the C4 dataset. The model is further trained on Jina AI's collection of more than 400 millions of sentence pairs and hard negatives. These pairs were obtained from various domains and were carefully selected through a thorough cleaning process. The embedding model was trained using 512 sequence length, but extrapolates to 8k sequence length (or even longer) thanks to ALiBi. This makes our model useful for a range of use cases, especially when processing long documents is needed, including long document retrieval, semantic textual similarity, text reranking, recommendation, RAG and LLM-based generative search, etc.
번역 대기 중 · 원문 표시
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。
기본 정보 등록 · 상세 정보 보완 예정
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。
기본 정보 등록 · 상세 정보 보완 예정
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。
기본 정보 등록 · 상세 정보 보완 예정
제공사, 분류, 입출력 조건을 조정하세요. 새 모델이 계속 등록됩니다.
월간 토큰 사용량으로 예상 API 비용을 비교하세요.
수집된 백만 토큰당 USD 요금입니다. 캐시 할인, 구간 요금, 추가 추론 출력, 세금은 제외됩니다. 최신 요금은 출처에서 확인하세요.
입력, 출력, 캐시 요금을 구분하고 동일 작업량으로 비교하세요. 이미지, 음성, 영상은 개수, 시간, 해상도로 과금될 수 있습니다.
반드시 그렇지는 않습니다. 버전별 라이선스, 상업 이용 제한, 정책을 확인하세요. 자체 호스팅에는 연산 및 유지 비용도 듭니다.
순위는 작업, 버전, 평가 방식에 따라 다릅니다. 실제 업무로 정확도, 지연, 안정성, 비용을 비교하세요.