Entries matching “fine-tuning”

Hugging Face's launch post covers day-0 transformers, llama.cpp and vLLM support, Inference Endpoints, speculative decoding, TRL fine-tuning and agent demos for Muse Glimmer.

Unsloth AI

@UnslothAI

You can now fine-tune Meta Muse Glimmer 30B for free! 🔥 Our free notebook also supports GRPO RL training. Unsloth trains Muse Glimmer 1.5× faster with 50% less VRAM vs FA2 setups. Train locally with 24GB VRAM. Guide: unsloth.ai/docs/models/mu… Notebooks: unsloth.ai/docs/models/mu…

Valiant Labs' Esper 4 agentic coding fine-tune of Muse Glimmer 30B.

Unsloth's bitsandbytes 4-bit build of Muse Glimmer 30B for fine-tuning and inference.

sequelbox's Tachibana-Agent fine-tune of Muse Glimmer 30B, part of a series also released for Gemma 4 12B and Qwen3.6 27B.

Fine-tune of Muse Glimmer 30B for Hermes Agent and agentic tool work that teaches the model to call one or two tools and stop.

@brn715

@brn715

A deliberately overengineered parody that 'gives you the Zuck', with a deterministic Oracle edition, a prompted Muse Glimmer edition and an MLX QLoRA fine-tune of Muse Glimmer 30B for Apple Silicon.

Sediment's fine-tune of Muse Glimmer 30B that answers factual questions when confident and says "I don't know" otherwise, calibrated for the AA-Omniscience setting.

@Satgoy152

@Satgoy152

A project that fine-tunes a DSpark speculator for Muse Glimmer 30B on on-policy coding and agentic traces to raise acceptance length on agentic workloads, evaluated with Terminal-Bench.

NVIDIA's technical blog reports Muse Glimmer serving over 20K tokens/sec on a single Blackwell Ultra GPU and covers RTX 5090, DGX Spark, DGX Station and Jetson deployments.

Sumanth

@Sumanth_077

Run and fine-tune Meta's Muse Glimmer locally! Meta released Muse Glimmer, a 30B dense vision model designed for local agentic and coding workflows. The first open model from Meta Superintelligence Labs, released under Apache 2.0. The model runs locally at different memory

A DPO fine-tune of Muse Glimmer focused on prose quality and humanlike characters, trained on roughly one-third writing and two-thirds roleplay data.

merve

@mervenoyann

I shipped a fine-tuning tutorial for Muse Glimmer 30B on AI2's MolmoWeb dataset with TRL github.com/merveenoyan/sm… > but merve, this model is sota on ScreenSpot-Pro? yes, but it doesn't work well with ambiguous prompts of MolmoWeb that are close to how you interact with computer,

A static Space showing a Hermes-agentic fine-tune of Muse Glimmer 30B proposing one or two tool calls or answering directly; the model card reports 16/20 on a simulated loop gate.

DFlash2 drafter for Muse Glimmer 30B fine-tuned on long-horizon, on-policy software-engineering traces to speed up coding workloads.

Muse Glimmer 30B fine-tuned on agentic coding traces and chat distilled from Claude Fable 5, merged bf16 and drop-in for the base.

@vcruz305

@vcruz305

Tested SGLang and vLLM launch recipes for an NVFP4 export of a Hermes-agentic fine-tune of Muse-Glimmer-30B on NVIDIA DGX Spark (GB10).

A Muse Glimmer fine-tune that writes, tunes and translates detection rules (Sigma to KQL and SPL, YARA, Wazuh) and runs 4-bit on a single 24 GB card.

merve

@mervenoyann

Meta released Muse Glimmer 30B: multimodal model for your Claw/Pi setups 🔥 we tested and fine-tuned the model for you, and shipped day-0 support in transformers and llama.cpp, including DFlash for 2-4x speed-ups 🥵 read our blog huggingface.co/blog/muse-glim…

A coding-specialised speculative-decoding drafter for Muse Glimmer 30B, fine-tuned on software-engineering traces. It raises mean acceptance length to about 6.9 versus 4.0 for the community DSpark, for about 3.8x over no speculation.