Model Card for Muse-Glimmer-30B-Hermes-Agentic-GGUF
This is an improved fine-tune of Muse Glimmer 30B for Hermes Agent and other agentic tool work. llama.cpp K-quants of the merged 16-bit student. Start with Q4_K_M on a 24 GB card.
Stock Muse Glimmer already speaks OpenAI-style tools. On hermes-agentic-bench the failure was the opposite of “won’t use tools”: simulated traces hit the consecutive-tool cap with an empty user answer (7/20, 7 HIT_CAP). Inside Hermes the same weights were already better at stopping (native 4/5, mean 2.8 tools). This student is trained to call one or two Hermes-named tools and stop.
I trained it on Unsloth’s free Muse Glimmer Conversational notebook (train docs) on Kaggle 2×T4. The stock notebook is FineTome chat; this run uses vcruz305/hermes-agentic-tool-sft (1,980 rows), apply_chat_template(..., tools=tools), and train_on_responses_only from <|start|>assistant so tool-call turns actually train.
Need llama.cpp ≥ b10353 (#26841). Leave DFlash off when scoring Hermes tool loops.
Model Details
- Developed by: Victor Cruz (vcruz305)
- Base developed by: Meta Superintelligence Lab — Muse Glimmer 30B
- 16-bit merge (full card): vcruz305/Muse-Glimmer-30B-Hermes-Agentic
- License: Apache 2.0
- Language(s): English SFT. Base is multilingual; this mix is English.
Model Sources
- This repo: https://huggingface.co/vcruz305/Muse-Glimmer-30B-Hermes-Agentic-GGUF
- SFT data: https://huggingface.co/datasets/vcruz305/hermes-agentic-tool-sft
- Eval: https://github.com/vcruz305/hermes-agentic-bench
- Train notebook: Unsloth Muse Glimmer Conversational
Why this fine-tune
I run a local Hermes Agent fleet (Telegram, tools, long sessions). Stock Muse is strong at emitting tool calls. The bench failure was loops:
- Open-ended
terminal/searchtraces hit the 12-turn cap with an empty user answer - Native Hermes was already better at stopping, so the gap was weights + pipe, not “Muse cannot tool-call”
- Community Muse+Hermes reports matched that: loops and unparsed ATEM, not silence
The student: stop after 1–2 Hermes tools, don’t retry a dead tool, recover once from a missing file, don’t invent extra echo hi on “do not use tools.”
Evaluation
Same llama.cpp recipe for stock vs this FT: Q4 class, DFlash off, 32k. Native scores from real hermes chat (footer + session DB).
| Battery | Stock Muse Glimmer | This fine-tune |
|---|---|---|
Simulated hermes_loop_gate.py (20) | 7/20 · mean 5.7 tools · 7 HIT_CAP | 16/20 · mean 1.05 · 0 HIT_CAP |
Native hermes_native_battery.py | 4/5 · mean 2.8 | 7/7 · mean 1.43 · 0 HIT_CAP |
Native 7/7: web (one search), no-tool math, missing-file stop, list-once, plan-only, no-tool definition, refuse-delete. This is not a re-run of Meta’s MCP Atlas / SWE-Bench table — those stay on the base card. Re-score on your box.
How to Get Started
./llama-cli --version # need >= b10353
hf download vcruz305/Muse-Glimmer-30B-Hermes-Agentic-GGUF \
--local-dir Muse-Hermes-GGUF \
--include "Muse-Glimmer-30B-Hermes-Agentic-Q4_K_M.gguf"
./llama-server \
-m Muse-Hermes-GGUF/Muse-Glimmer-30B-Hermes-Agentic-Q4_K_M.gguf \
-a muse-glimmer-30b \
--host 127.0.0.1 --port 8084 \
-ngl 99 -c 32768 -np 1 --jinja \
--temp 0.6 --top-p 0.95 --top-k 64
Hermes provider: http://127.0.0.1:8084/v1, model id muse-glimmer-30b.
| Use | temp | top_p | top_k |
|---|---|---|---|
| Meta default | 1.0 | 0.95 | 64 |
| Hermes loop-gate / this eval | 0.6 | 0.95 | 64 |
Files
| File | Bit class | Start here if |
|---|---|---|
Muse-Glimmer-30B-Hermes-Agentic-Q4_K_M.gguf | 4 | 24 GB card |
Muse-Glimmer-30B-Hermes-Agentic-Q5_K_M.gguf | 5 | 24–32 GB |
Muse-Glimmer-30B-Hermes-Agentic-Q6_K.gguf | 6 | 32 GB+ |
Muse-Glimmer-30B-Hermes-Agentic-Q8_0.gguf | 8 | near-lossless |
Muse-Glimmer-30B-Hermes-Agentic-Q3_K_M.gguf | 3 | 16 GB class |
Muse-Glimmer-30B-Hermes-Agentic-Q2_K.gguf | 2 | smallest usable K-quant |
Muse-Glimmer-30B-Hermes-Agentic-F16.gguf | 16 | reconvert / research |
Training Details
Unsloth free Muse Conversational notebook, Kaggle 2×T4, QLoRA r=8, 392 steps (1 epoch), loss 0.163, ~3 h 38 m. Dataset vcruz305/hermes-agentic-tool-sft. Full procedure: 16-bit card.
Model Card Authors / Contact
Victor Cruz. This page or https://github.com/vcruz305/hermes-agentic-bench.
Acknowledgements
Meta Superintelligence Lab (Muse Glimmer, Apache 2.0). Unsloth free Muse notebook. Nous Research Hermes Agent.