Soraya Hoggarth

somersetent's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a dataset about 1 month ago

r0b0tlab/qwen3.8-max-glm5.2-kimi-k3-distillation

Viewer • Updated Aug 2 • 22.9M • 4k • 267

updated 3 collections about 1 month ago

Quantization/Quantized

Collection

Quantization in LLMs compresses model weights from high-precision formats (like 16-bit) to lower-precision formats (like 8-bit or 4-bit). • 440 items • Updated Aug 27

Fine-tuning/Fine-tuned

Collection

Fine-tuning generative AI is the process of taking a pre-trained base model and training it further on a smaller, specific dataset. • 335 items • Updated Aug 27

Alibaba-Tongyi-Qwen

Collection

398 items • Updated Aug 16

liked 2 models about 1 month ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 6.84M • • 16.5k

unsloth/Qwen3.8-27B-GGUF

27B • Updated Aug 20 • 6.54M • 4.71k

updated 5 collections about 1 month ago

Importance Matrix (Imatrix)

Collection

The Importance Matrix (iMatrix) is a data-driven calibration method used in low-bit quantization for LLMs. • 330 items • Updated Aug 16

GPT-Generated Unified Format (GGUF)

Collection

GPT-Generated Unified Format (GGUF) is a single-file binary format used to store and run large language models efficiently on consumer hardware. • 706 items • Updated 21 days ago

Quantization/Quantized

Collection

Quantization in LLMs compresses model weights from high-precision formats (like 16-bit) to lower-precision formats (like 8-bit or 4-bit). • 440 items • Updated Aug 27

Alibaba-Tongyi-Qwen

Collection

398 items • Updated Aug 16

Mixture of Experts (MoE)

Collection

Mixture of Experts (MoE) is a machine learning architecture that splits a large neural network into smaller sub-networks called "experts." • 202 items • Updated Aug 16

liked a model about 1 month ago

Qwen/Qwen3.8-2.4T-A95B

Text Generation • 2.4T • Updated Aug 12 • 43.6k • • 1.27k

updated 3 collections about 2 months ago

NVIDIA-Nemotron

Collection

25 items • Updated Aug 14

GPT-Generated Unified Format (GGUF)

Collection

GPT-Generated Unified Format (GGUF) is a single-file binary format used to store and run large language models efficiently on consumer hardware. • 706 items • Updated 21 days ago

Automatic-Speech-Recognition (ASR)

Collection

Automatic Speech Recognition (ASR) converts spoken audio into text. In generative AI advanced ASR models act as the ears of large multimodal models. • 5 items • Updated Aug 14

liked a model about 2 months ago

nvidia/nemotron-speech-streaming-en-0.6b

Automatic Speech Recognition • 0.6B • Updated Aug 5 • 381k • 630

updated 3 collections about 2 months ago

Agentic Generative AI

Collection

Agentic generative AI refers to autonomous systems built on LLMs that can plan, use tools, and execute multi-step workflows. • 57 items • Updated Aug 11

Fine-tuning/Fine-tuned

Collection

Fine-tuning generative AI is the process of taking a pre-trained base model and training it further on a smaller, specific dataset. • 335 items • Updated Aug 27

Quantization/Quantized

Collection

Quantization in LLMs compresses model weights from high-precision formats (like 16-bit) to lower-precision formats (like 8-bit or 4-bit). • 440 items • Updated Aug 27