Instructions to use yeasah/Muse-Glimmer-30B-exl3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yeasah/Muse-Glimmer-30B-exl3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="yeasah/Muse-Glimmer-30B-exl3")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("yeasah/Muse-Glimmer-30B-exl3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use yeasah/Muse-Glimmer-30B-exl3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "yeasah/Muse-Glimmer-30B-exl3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yeasah/Muse-Glimmer-30B-exl3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/yeasah/Muse-Glimmer-30B-exl3
- SGLang
How to use yeasah/Muse-Glimmer-30B-exl3 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "yeasah/Muse-Glimmer-30B-exl3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yeasah/Muse-Glimmer-30B-exl3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "yeasah/Muse-Glimmer-30B-exl3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yeasah/Muse-Glimmer-30B-exl3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use yeasah/Muse-Glimmer-30B-exl3 with Docker Model Runner:
docker model run hf.co/yeasah/Muse-Glimmer-30B-exl3
Download qb_loop.json from yeasah/Muse-Glimmer-30B-exl3: direct link, hf CLI and curl.
- Browser
- Download file 12.5 kB
-
https://huggingface.co/yeasah/Muse-Glimmer-30B-exl3/resolve/main/qb_loop.json
- Command line
-
hf download hf://yeasah/Muse-Glimmer-30B-exl3/qb_loop.json
-
curl -L -o qb_loop.json https://huggingface.co/yeasah/Muse-Glimmer-30B-exl3/resolve/main/qb_loop.json
12.5 kB
| [ | |
| { | |
| "label": "HF BF16", | |
| "group": "reference", | |
| "ppl": 1.4537124292335843, | |
| "bpw_layer": 16.0, | |
| "bpw_head": 16.0, | |
| "bpw_embed": 16.0, | |
| "vram_gb": 51.8809814453125 | |
| }, | |
| { | |
| "label": "Noise floor", | |
| "group": "noise_floor", | |
| "ppl": 1.4541207211523837, | |
| "kld": 0.0009864644380286336, | |
| "kld_median": 1.9364728359505534e-05, | |
| "kld_p10": -1.4288778160675975e-08, | |
| "kld_p25": 6.018034959254237e-09, | |
| "kld_p75": 0.0007447852985933423, | |
| "kld_p90": 0.0023612421937286854, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.007228116504848003, | |
| "mean": 0.0038772053085267544, | |
| "median": 0.00208185613155365 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10195623338222504, | |
| "mean": 0.0030946233309805393, | |
| "median": 0.0018332060426473618 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1567307710647583, | |
| "mean": 0.002460634568706155, | |
| "median": 0.0012941202148795128 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.16001325845718384, | |
| "mean": 0.0014340706402435899, | |
| "median": 0.0004925797693431377 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5740716457366943, | |
| "mean": 4.841867121285759e-05, | |
| "median": 4.3649880154816856e-08 | |
| } | |
| ], | |
| "bpw_layer": 16.0, | |
| "bpw_head": 16.0, | |
| "bpw_embed": 16.0, | |
| "vram_gb": 51.8809814453125 | |
| }, | |
| { | |
| "label": "2.50bpw-H5", | |
| "group": "EXL3", | |
| "ppl": 1.5525304052681332, | |
| "kld": 0.060127321630716324, | |
| "kld_median": 0.005317793693393469, | |
| "kld_p10": -7.528146439561567e-10, | |
| "kld_p25": 3.0852813779347343e-06, | |
| "kld_p75": 0.051220428198575974, | |
| "kld_p90": 0.15335431694984436, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.007228116504848003, | |
| "mean": 0.12011552602052689, | |
| "median": 0.08013651520013809 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10195623338222504, | |
| "mean": 0.14943969249725342, | |
| "median": 0.07692268490791321 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1567307710647583, | |
| "mean": 0.14146967232227325, | |
| "median": 0.06351218372583389 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.16001325845718384, | |
| "mean": 0.10080434381961823, | |
| "median": 0.03970298916101456 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5740716457366943, | |
| "mean": 0.009964123368263245, | |
| "median": 1.0026313248090446e-05 | |
| } | |
| ], | |
| "bpw_layer": 2.504164938549567, | |
| "bpw_head": 5.00248303396898, | |
| "bpw_embed": 16.0, | |
| "vram_gb": 10.624184969812632, | |
| "on_disk_gb": 14.20649278536439, | |
| "unexplained_gb": 0.0, | |
| "expected_absent_gb": 3.582307815551758 | |
| }, | |
| { | |
| "label": "3.00bpw-H5", | |
| "group": "EXL3", | |
| "ppl": 1.5009961654812252, | |
| "kld": 0.029938602820038795, | |
| "kld_median": 0.0017892372561618686, | |
| "kld_p10": -4.2500722940985725e-09, | |
| "kld_p25": 9.406167578163149e-07, | |
| "kld_p75": 0.024081652984023094, | |
| "kld_p90": 0.07775074988603592, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.007228116504848003, | |
| "mean": 0.06756498664617538, | |
| "median": 0.03998051583766937 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10195623338222504, | |
| "mean": 0.07986386865377426, | |
| "median": 0.04182257503271103 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1567307710647583, | |
| "mean": 0.07279659062623978, | |
| "median": 0.03258643299341202 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.16001325845718384, | |
| "mean": 0.04945489391684532, | |
| "median": 0.018136635422706604 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5740716457366943, | |
| "mean": 0.003457255195826292, | |
| "median": 2.5328192805318395e-06 | |
| } | |
| ], | |
| "bpw_layer": 3.004164938549567, | |
| "bpw_head": 5.00248303396898, | |
| "bpw_embed": 16.0, | |
| "vram_gb": 12.088906649500132, | |
| "on_disk_gb": 15.67121446505189, | |
| "unexplained_gb": 0.0, | |
| "expected_absent_gb": 3.582307815551758 | |
| }, | |
| { | |
| "label": "3.50bpw-H5", | |
| "group": "EXL3", | |
| "ppl": 1.4769175936710943, | |
| "kld": 0.01535273902118206, | |
| "kld_median": 0.0007882341742515564, | |
| "kld_p10": -6.507932859278753e-09, | |
| "kld_p25": 5.945149723629584e-07, | |
| "kld_p75": 0.011011114344000816, | |
| "kld_p90": 0.03763076663017273, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.007228116504848003, | |
| "mean": 0.03799666091799736, | |
| "median": 0.02044505625963211 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10195623338222504, | |
| "mean": 0.043119899928569794, | |
| "median": 0.020213397219777107 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1567307710647583, | |
| "mean": 0.038697075098752975, | |
| "median": 0.015811724588274956 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.16001325845718384, | |
| "mean": 0.024036474525928497, | |
| "median": 0.007971270941197872 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5740716457366943, | |
| "mean": 0.001342296483926475, | |
| "median": 1.3616885325973271e-06 | |
| } | |
| ], | |
| "bpw_layer": 3.504164938549567, | |
| "bpw_head": 5.00248303396898, | |
| "bpw_embed": 16.0, | |
| "vram_gb": 13.553628329187632, | |
| "on_disk_gb": 17.13593614473939, | |
| "unexplained_gb": 0.0, | |
| "expected_absent_gb": 3.582307815551758 | |
| }, | |
| { | |
| "label": "4.00bpw", | |
| "group": "EXL3", | |
| "ppl": 1.4637401945249038, | |
| "kld": 0.008392944000661373, | |
| "kld_median": 0.00039177568396553397, | |
| "kld_p10": -6.348859216132041e-09, | |
| "kld_p25": 1.8873811313824262e-07, | |
| "kld_p75": 0.006523226387798786, | |
| "kld_p90": 0.02126849815249443, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.007228116504848003, | |
| "mean": 0.02017896994948387, | |
| "median": 0.011596226133406162 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10195623338222504, | |
| "mean": 0.025072157382965088, | |
| "median": 0.012377439066767693 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1567307710647583, | |
| "mean": 0.021166503429412842, | |
| "median": 0.009088150225579739 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.16001325845718384, | |
| "mean": 0.012652509845793247, | |
| "median": 0.004736634436994791 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5740716457366943, | |
| "mean": 0.000607611786108464, | |
| "median": 7.135414534786833e-07 | |
| } | |
| ], | |
| "bpw_layer": 4.004164938549566, | |
| "bpw_head": 6.00248303396898, | |
| "bpw_embed": 16.0, | |
| "vram_gb": 15.1749585904181, | |
| "on_disk_gb": 18.757266405969858, | |
| "unexplained_gb": 0.0, | |
| "expected_absent_gb": 3.582307815551758 | |
| }, | |
| { | |
| "label": "5.00bpw", | |
| "group": "EXL3", | |
| "ppl": 1.4583473712626838, | |
| "kld": 0.003013565205037594, | |
| "kld_median": 0.0001269974745810032, | |
| "kld_p10": -4.468162284609889e-09, | |
| "kld_p25": 5.7585893387113174e-08, | |
| "kld_p75": 0.0022457181476056576, | |
| "kld_p90": 0.00732620432972908, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.007228116504848003, | |
| "mean": 0.008818966336548328, | |
| "median": 0.004800174385309219 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10195623338222504, | |
| "mean": 0.009530628100037575, | |
| "median": 0.004604881629347801 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1567307710647583, | |
| "mean": 0.007489053066819906, | |
| "median": 0.003256740979850292 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.16001325845718384, | |
| "mean": 0.004394567105919123, | |
| "median": 0.0015704464167356491 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5740716457366943, | |
| "mean": 0.0001762138563208282, | |
| "median": 2.773047071968904e-07 | |
| } | |
| ], | |
| "bpw_layer": 5.004164938549566, | |
| "bpw_head": 6.00248303396898, | |
| "bpw_embed": 16.0, | |
| "vram_gb": 18.1044019497931, | |
| "on_disk_gb": 21.686709765344858, | |
| "unexplained_gb": 0.0, | |
| "expected_absent_gb": 3.582307815551758 | |
| }, | |
| { | |
| "label": "6.00bpw", | |
| "group": "EXL3", | |
| "ppl": 1.4543338544862172, | |
| "kld": 0.0014518136158585548, | |
| "kld_median": 5.730659904656932e-05, | |
| "kld_p10": -1.1547489187080373e-08, | |
| "kld_p25": 1.3450054403563172e-08, | |
| "kld_p75": 0.0010957991471514106, | |
| "kld_p90": 0.0035184023436158895, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.007228116504848003, | |
| "mean": 0.005015292204916477, | |
| "median": 0.002551216632127762 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10195623338222504, | |
| "mean": 0.004677505698055029, | |
| "median": 0.002421582117676735 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1567307710647583, | |
| "mean": 0.0037032479885965586, | |
| "median": 0.0015639718621969223 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.16001325845718384, | |
| "mean": 0.0019560765940696, | |
| "median": 0.0007100282236933708 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5740716457366943, | |
| "mean": 7.882397767389193e-05, | |
| "median": 1.0261060623406593e-07 | |
| } | |
| ], | |
| "bpw_layer": 6.004164938549566, | |
| "bpw_head": 6.00248303396898, | |
| "bpw_embed": 16.0, | |
| "vram_gb": 21.0338453091681, | |
| "on_disk_gb": 24.616153124719858, | |
| "unexplained_gb": 0.0, | |
| "expected_absent_gb": 3.582307815551758 | |
| }, | |
| { | |
| "label": "thr:RedHatAI/Muse-Glimmer-30B-FP8-block", | |
| "group": "threshold", | |
| "ppl": 1.461262703485035, | |
| "kld": 0.00632255245000124, | |
| "kld_median": 0.00023239667643792927, | |
| "kld_p10": -5.569200212107717e-09, | |
| "kld_p25": 8.278188801114084e-08, | |
| "kld_p75": 0.004652041010558605, | |
| "kld_p90": 0.014667397364974022, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.007228116504848003, | |
| "mean": 0.017401989549398422, | |
| "median": 0.0108877532184124 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10195623338222504, | |
| "mean": 0.01790522411465645, | |
| "median": 0.009256819263100624 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1567307710647583, | |
| "mean": 0.014396267011761665, | |
| "median": 0.0069038355723023415 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.16001325845718384, | |
| "mean": 0.009438563138246536, | |
| "median": 0.003366498276591301 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5740716457366943, | |
| "mean": 0.001053155167028308, | |
| "median": 4.4771684315492166e-07 | |
| } | |
| ], | |
| "bpw_layer": 8.001953125, | |
| "bpw_head": 16.0, | |
| "bpw_embed": 16.0, | |
| "vram_gb": 28.45115613937378 | |
| } | |
| ] |