bloomz-3b-GGUF/README.md

base_model, datasets, language, license, pipeline_tag, tags, programming_language, widget, model-index

base_model	datasets	language	license	pipeline_tag	tags	programming_language	widget	model-index
bigscience/bloomz-3b	bigscience/xP3	ak ar as bm bn ca code en es eu fon fr gu hi id ig ki kn lg ln ml mr ne nso ny or pa pt rn rw sn st sw ta te tn ts tum tw ur vi wo xh yo zh zu	bigscience-bloom-rail-1.0	text-generation	llama-cpp matrixportal	C C++ C# Go Java JavaScript Lua PHP Python Ruby Rust Scala TypeScript	text example_title 一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。Would you rate the previous review as positive, neutral or negative? zh-en sentiment text example_title 一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。你认为这句话的立场是赞扬、中立还是批评？ zh-zh sentiment text example_title Suggest at least five related search terms to "Mạng neural nhân tạo". vi-en query text example_title Proposez au moins cinq mots clés concernant «Réseau de neurones artificiels». fr-fr query text example_title Explain in a sentence in Telugu what is backpropagation in neural networks. te-en qa text example_title Why is the sky blue? en-en qa text example_title Write a fairy tale about a troll saving a princess from a dangerous dragon. The fairy tale is a masterpiece that has achieved praise worldwide and its moral is "Heroes Come in All Shapes and Sizes". Story (in Spanish): es-en fable text example_title Write a fable about wood elves living in a forest that is suddenly invaded by ogres. The fable is a masterpiece that has achieved praise worldwide and its moral is "Violence is the last refuge of the incompetent". Fable (in Hindi): hi-en fable	name results bloomz-3b1 task dataset metrics type Coreference resolution name type config split revision Winogrande XL (xl) winogrande xl validation a80f460359d1e9a67c006011c94de42a8759430c type value Accuracy 53.67 task dataset metrics type Coreference resolution name type config split revision XWinograd (en) Muennighoff/xwinograd en test 9dd5ea5505fad86b7bedad667955577815300cee type value Accuracy 59.23 task dataset metrics type Coreference resolution name type config split revision XWinograd (fr) Muennighoff/xwinograd fr test 9dd5ea5505fad86b7bedad667955577815300cee type value Accuracy 53.01 task dataset metrics type Coreference resolution name type config split revision XWinograd (jp) Muennighoff/xwinograd jp test 9dd5ea5505fad86b7bedad667955577815300cee type value Accuracy 52.45 task dataset metrics type Coreference resolution name type config split revision XWinograd (pt) Muennighoff/xwinograd pt test 9dd5ea5505fad86b7bedad667955577815300cee type value Accuracy 53.61 task dataset metrics type Coreference resolution name type config split revision XWinograd (ru) Muennighoff/xwinograd ru test 9dd5ea5505fad86b7bedad667955577815300cee type value Accuracy 53.97 task dataset metrics type Coreference resolution name type config split revision XWinograd (zh) Muennighoff/xwinograd zh test 9dd5ea5505fad86b7bedad667955577815300cee type value Accuracy 60.91 task dataset metrics type Natural language inference name type config split revision ANLI (r1) anli r1 validation 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094 type value Accuracy 40.1 task dataset metrics type Natural language inference name type config split revision ANLI (r2) anli r2 validation 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094 type value Accuracy 36.8 task dataset metrics type Natural language inference name type config split revision ANLI (r3) anli r3 validation 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094 type value Accuracy 40.0 task dataset metrics type Natural language inference name type config split revision SuperGLUE (cb) super_glue cb validation 9e12063561e7e6c79099feb6d5a493142584e9e2 type value Accuracy 75.0 task dataset metrics type Natural language inference name type config split revision SuperGLUE (rte) super_glue rte validation 9e12063561e7e6c79099feb6d5a493142584e9e2 type value Accuracy 76.17 task dataset metrics type Natural language inference name type config split revision XNLI (ar) xnli ar validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 53.29 task dataset metrics type Natural language inference name type config split revision XNLI (bg) xnli bg validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 43.82 task dataset metrics type Natural language inference name type config split revision XNLI (de) xnli de validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 45.26 task dataset metrics type Natural language inference name type config split revision XNLI (el) xnli el validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 42.61 task dataset metrics type Natural language inference name type config split revision XNLI (en) xnli en validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 57.31 task dataset metrics type Natural language inference name type config split revision XNLI (es) xnli es validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 56.14 task dataset metrics type Natural language inference name type config split revision XNLI (fr) xnli fr validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 55.78 task dataset metrics type Natural language inference name type config split revision XNLI (hi) xnli hi validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 51.49 task dataset metrics type Natural language inference name type config split revision XNLI (ru) xnli ru validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 47.11 task dataset metrics type Natural language inference name type config split revision XNLI (sw) xnli sw validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 47.83 task dataset metrics type Natural language inference name type config split revision XNLI (th) xnli th validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 42.93 task dataset metrics type Natural language inference name type config split revision XNLI (tr) xnli tr validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 37.23 task dataset metrics type Natural language inference name type config split revision XNLI (ur) xnli ur validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 49.04 task dataset metrics type Natural language inference name type config split revision XNLI (vi) xnli vi validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 53.98 task dataset metrics type Natural language inference name type config split revision XNLI (zh) xnli zh validation a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16 type value Accuracy 54.18 task dataset metrics type Program synthesis name type config split revision HumanEval openai_humaneval None test e8dc562f5de170c54b5481011dd9f4fa04845771 type value Pass@1 6.29 type value Pass@10 11.94 type value Pass@100 19.06 task dataset metrics type Sentence completion name type config split revision StoryCloze (2016) story_cloze 2016 validation e724c6f8cdf7c7a2fb229d862226e15b023ee4db type value Accuracy 87.33 task dataset metrics type Sentence completion name type config split revision SuperGLUE (copa) super_glue copa validation 9e12063561e7e6c79099feb6d5a493142584e9e2 type value Accuracy 76.0 task dataset metrics type Sentence completion name type config split revision XCOPA (et) xcopa et validation 37f73c60fb123111fa5af5f9b705d0b3747fd187 type value Accuracy 53.0 task dataset metrics type Sentence completion name type config split revision XCOPA (ht) xcopa ht validation 37f73c60fb123111fa5af5f9b705d0b3747fd187 type value Accuracy 64.0 task dataset metrics type Sentence completion name type config split revision XCOPA (id) xcopa id validation 37f73c60fb123111fa5af5f9b705d0b3747fd187 type value Accuracy 70.0 task dataset metrics type Sentence completion name type config split revision XCOPA (it) xcopa it validation 37f73c60fb123111fa5af5f9b705d0b3747fd187 type value Accuracy 53.0 task dataset metrics type Sentence completion name type config split revision XCOPA (qu) xcopa qu validation 37f73c60fb123111fa5af5f9b705d0b3747fd187 type value Accuracy 56.0 task dataset metrics type Sentence completion name type config split revision XCOPA (sw) xcopa sw validation 37f73c60fb123111fa5af5f9b705d0b3747fd187 type value Accuracy 66.0 task dataset metrics type Sentence completion name type config split revision XCOPA (ta) xcopa ta validation 37f73c60fb123111fa5af5f9b705d0b3747fd187 type value Accuracy 59.0 task dataset metrics type Sentence completion name type config split revision XCOPA (th) xcopa th validation 37f73c60fb123111fa5af5f9b705d0b3747fd187 type value Accuracy 63.0 task dataset metrics type Sentence completion name type config split revision XCOPA (tr) xcopa tr validation 37f73c60fb123111fa5af5f9b705d0b3747fd187 type value Accuracy 61.0 task dataset metrics type Sentence completion name type config split revision XCOPA (vi) xcopa vi validation 37f73c60fb123111fa5af5f9b705d0b3747fd187 type value Accuracy 77.0 task dataset metrics type Sentence completion name type config split revision XCOPA (zh) xcopa zh validation 37f73c60fb123111fa5af5f9b705d0b3747fd187 type value Accuracy 73.0 task dataset metrics type Sentence completion name type config split revision XStoryCloze (ar) Muennighoff/xstory_cloze ar validation 8bb76e594b68147f1a430e86829d07189622b90d type value Accuracy 80.61 task dataset metrics type Sentence completion name type config split revision XStoryCloze (es) Muennighoff/xstory_cloze es validation 8bb76e594b68147f1a430e86829d07189622b90d type value Accuracy 85.9 task dataset metrics type Sentence completion name type config split revision XStoryCloze (eu) Muennighoff/xstory_cloze eu validation 8bb76e594b68147f1a430e86829d07189622b90d type value Accuracy 70.95 task dataset metrics type Sentence completion name type config split revision XStoryCloze (hi) Muennighoff/xstory_cloze hi validation 8bb76e594b68147f1a430e86829d07189622b90d type value Accuracy 78.89 task dataset metrics type Sentence completion name type config split revision XStoryCloze (id) Muennighoff/xstory_cloze id validation 8bb76e594b68147f1a430e86829d07189622b90d type value Accuracy 82.99 task dataset metrics type Sentence completion name type config split revision XStoryCloze (my) Muennighoff/xstory_cloze my validation 8bb76e594b68147f1a430e86829d07189622b90d type value Accuracy 49.9 task dataset metrics type Sentence completion name type config split revision XStoryCloze (ru) Muennighoff/xstory_cloze ru validation 8bb76e594b68147f1a430e86829d07189622b90d type value Accuracy 61.42 task dataset metrics type Sentence completion name type config split revision XStoryCloze (sw) Muennighoff/xstory_cloze sw validation 8bb76e594b68147f1a430e86829d07189622b90d type value Accuracy 69.69 task dataset metrics type Sentence completion name type config split revision XStoryCloze (te) Muennighoff/xstory_cloze te validation 8bb76e594b68147f1a430e86829d07189622b90d type value Accuracy 73.66 task dataset metrics type Sentence completion name type config split revision XStoryCloze (zh) Muennighoff/xstory_cloze zh validation 8bb76e594b68147f1a430e86829d07189622b90d type value Accuracy 84.32

ysn-rfd/bloomz-3b-GGUF

This model was converted to GGUF format from bigscience/bloomz-3b using llama.cpp via the ggml.ai's all-gguf-same-where space. Refer to the original model card for more details on the model.

✅ Quantized Models Download List

🔍 Recommended Quantizations

• ✨ General CPU Use: Q4_K_M (Best balance of speed/quality)
• 📱 ARM Devices: Q4_0 (Optimized for ARM CPUs)
• 🏆 Maximum Quality: Q8_0 (Near-original quality)

📦 Full Quantization Options

🚀 Download	🔢 Type	📝 Notes
Download		Basic quantization
Download		Small size
Download		Balanced quality
Download		Better quality
Download		Fast on ARM
Download		Fast, recommended
Download	⭐	Best balance
Download		Good quality
Download		Balanced
Download		High quality
Download	🏆	Very good quality
Download	⚡	Fast, best quality
Download		Maximum accuracy

💡 Tip: Use F16 for maximum precision when quality is critical

---

🚀 Applications and Tools for Locally Quantized LLMs

🖥️ Desktop Applications

Application	Description	Download Link
Llama.cpp	A fast and efficient inference engine for GGUF models.	GitHub Repository
Ollama	A streamlined solution for running LLMs locally.	Website
AnythingLLM	An AI-powered knowledge management tool.	GitHub Repository
Open WebUI	A user-friendly web interface for running local LLMs.	GitHub Repository
GPT4All	A user-friendly desktop application supporting various LLMs, compatible with GGUF models.	GitHub Repository
LM Studio	A desktop application designed to run and manage local LLMs, supporting GGUF format.	Website
GPT4All Chat	A chat application compatible with GGUF models for local, offline interactions.	GitHub Repository

---

📱 Mobile Applications

Application	Description	Download Link
ChatterUI	A simple and lightweight LLM app for mobile devices.	GitHub Repository
Maid	Mobile Artificial Intelligence Distribution for running AI models on mobile devices.	GitHub Repository
PocketPal AI	A mobile AI assistant powered by local models.	GitHub Repository
Layla	A flexible platform for running various AI models on mobile devices.	Website

---

🎨 Image Generation Applications

Application	Description	Download Link
Stable Diffusion	An open-source AI model for generating images from text.	GitHub Repository
Stable Diffusion WebUI	A web application providing access to Stable Diffusion models via a browser interface.	GitHub Repository
Local Dream	Android Stable Diffusion with Snapdragon NPU acceleration. Also supports CPU inference.	GitHub Repository
Stable-Diffusion-Android (SDAI)	An open-source AI art application for Android devices, enabling digital art creation.	GitHub Repository

---