Felladrin

Model creator: Jina AI Original model: jina-reranker-v1-tiny-en GGUF quantization: based on llama.cpp release f4d2b This model is designed for blazing-fast reranking while maintaining competitive performance. What's more, it leverages the power of our JinaBERT model as its foundation. `JinaBERT` itself is a unique variant of the BERT architecture that supports the symmetric bidirectional variant of ALiBi. This allows `jina-reranker-v1-tiny-en` to process significantly longer sequences of text compared to other reranking models, up to an impressive 8,192 tokens. To achieve the remarkable speed, the `jina-reranker-v1-tiny-en` employ a technique called knowledge distillation. Here, a complex, but slower, model (like our original jina-reranker-v1-base-en) acts as a teacher, condensing its knowledge into a smaller, faster student model. This student retains most of the teacher's knowledge, allowing it to deliver similar accuracy in a fraction of the time. Here's a breakdown of the reranker models we provide: | Model Name | Layers | Hidden Size | Parameters (Millions) | | ------------------------------------------------------------------------------------ | ------ | ----------- | --------------------- | | jina-reranker-v1-base-en | 12 | 768 | 137.0 | | jina-reranker-v1-turbo-en | 6 | 384 | 37.8 | | jina-reranker-v1-tiny-en | 4 | 384 | 33.0 | > Currently, the `jina-reranker-v1-base-en` model is not available on Hugging Face. You can access it via the Jina AI Reranker API. As you can see, the `jina-reranker-v1-turbo-en` offers a balanced approach with 6 layers and 37.8 million parameters. This translates to fast search and reranking while preserving a high degree of accuracy. The `jina-reranker-v1-tiny-en` prioritizes speed even further, achieving the fastest inference speeds with its 4-layer, 33.0 million parameter architecture. This makes it ideal for scenarios where absolute top accuracy is less crucial. 1. The easiest way to starting using `jina-reranker-v1-tiny-en` is to use Jina AI's Reranker API. 2. Alternatively, you can use the latest version of the `sentence-transformers>=0.27.0` library. You can install it via pip: Then, you can use the following code to interact with the model: 3. You can also use the `transformers` library to interact with the model programmatically. 4. You can also use the `transformers.js` library to run the model directly in JavaScript (in-browser, Node.js, Deno, etc.)! If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Then, you can use the following code to interact with the model: That's it! You can now use the `jina-reranker-v1-tiny-en` model in your projects. We evaluated Jina Reranker on 3 key benchmarks to ensure top-tier performance and search relevance. | Model Name | NDCG@10 (17 BEIR datasets) | NDCG@10 (5 LoCo datasets) | Hit Rate (LlamaIndex RAG) | | ------------------------------------------ | -------------------------- | ------------------------- | ------------------------- | | `jina-reranker-v1-base-en` | 52.45 | 87.31 | 85.53 | | `jina-reranker-v1-turbo-en` | 49.60 | 69.21 | 85.13 | | `jina-reranker-v1-tiny-en` (you are here) | 48.54 | 70.29 | 85.00 | | `mxbai-rerank-base-v1` | 49.19 | - | 82.50 | | `mxbai-rerank-xsmall-v1` | 48.80 | - | 83.69 | | `ms-marco-MiniLM-L-6-v2` | 48.64 | - | 82.63 | | `ms-marco-MiniLM-L-4-v2` | 47.81 | - | 83.82 | | `bge-reranker-base` | 47.89 | - | 83.03 | - `NDCG@10` is a measure of ranking quality, with higher scores indicating better search results. `Hit Rate` measures the percentage of relevant documents that appear in the top 10 search results. - The results of LoCo datasets on other models are not available since they do not support long documents more than 512 tokens. For more details, please refer to our benchmarking sheets. Join our Discord community and chat with other community members about ideas.

Language: en License: apache-2.0

GGUF version of HuggingFaceTB/SmolLM2-360M-Instruct.

Felladrin/MiniCPM4-0.5B-QAT-Int4-unquantized-Q4KS-GGUF This model was converted to GGUF format from `openbmb/MiniCPM4-0.5B-QAT-Int4-unquantized` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

Language model with Apache 2.0 license.

Felladrin/gguf-Q5KM-Qwen3-4B-Merge-Variant-01 This model was converted to GGUF format from `Felladrin/Qwen3-4B-Merge-Variant-01` using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMACURL=1` flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

Sharded GGUF version of bartowski/arcee-aiAFM-4.5B-GGUF.

Sharded GGUF version of bartowski/googlegemma-3-270m-it-GGUF.

Sharded GGUF version of unsloth/Phi-4-mini-reasoning-GGUF.

Sharded GGUF version of Felladrin/MiniCPM4-0.5B-QAT-Int4-unquantized-Q4KS-GGUF.

GGUF version of HuggingFaceTB/SmolLM2-1.7B-Instruct.

Sharded GGUF version of bartowski/HuggingFaceTBSmolLM3-3B-GGUF.

Sharded GGUF version of bartowski/nvidiaLlama-3.1-Nemotron-Nano-4B-v1.1-GGUF.

Sharded GGUF version of bartowski/granite-3.0-3b-a800m-instruct-GGUF.

GGUF version of HuggingFaceTB/SmolLM2-135M-Instruct.

Sharded GGUF version of bartowski/googlegemma-3n-E2B-it-GGUF.

Sharded GGUF version of mradermacher/Falcon-H1-0.5B-Instruct-i1-GGUF.

Sharded GGUF version of QuantFactory/jais-adapted-7b-chat-GGUF.

Sharded GGUF version of internlm/internlm25-18b-chat-gguf.

Sharded GGUF version of bartowski/AMD-OLMo-1B-SFT-DPO-GGUF.

Sharded GGUF version of bartowski/SmolLM2-360M-Instruct-GGUF.

Sharded GGUF version of Felladrin/gguf-pythia-1.4b-sft-full.

Sharded GGUF version of second-state/stablelm-2-zephyr-1.6b-GGUF.