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_ctx_user.json from yeasah/Muse-Glimmer-30B-exl3: direct link, hf CLI and curl.
- Browser
- Download file 12.4 kB
-
https://huggingface.co/yeasah/Muse-Glimmer-30B-exl3/resolve/main/qb_ctx_user.json
- Command line
-
hf download hf://yeasah/Muse-Glimmer-30B-exl3/qb_ctx_user.json
-
curl -L -o qb_ctx_user.json https://huggingface.co/yeasah/Muse-Glimmer-30B-exl3/resolve/main/qb_ctx_user.json
12.4 kB
| [ | |
| { | |
| "label": "HF BF16", | |
| "group": "reference", | |
| "ppl": 1.4511780387387494, | |
| "bpw_layer": 16.0, | |
| "bpw_head": 16.0, | |
| "bpw_embed": 16.0, | |
| "vram_gb": 51.8809814453125 | |
| }, | |
| { | |
| "label": "Noise floor", | |
| "group": "noise_floor", | |
| "ppl": 1.4508537293341592, | |
| "kld": 0.000983338337391615, | |
| "kld_median": 1.0956617188639939e-05, | |
| "kld_p10": -1.8294448622668824e-08, | |
| "kld_p25": 5.099890287851849e-09, | |
| "kld_p75": 0.0007007386302575469, | |
| "kld_p90": 0.0023765787482261658, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.009831426665186882, | |
| "mean": 0.004094546660780907, | |
| "median": 0.0020812158472836018 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10216876864433289, | |
| "mean": 0.0033511724323034286, | |
| "median": 0.0018871147185564041 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1491546928882599, | |
| "mean": 0.002595909172669053, | |
| "median": 0.0013477244647219777 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.1448366641998291, | |
| "mean": 0.0012761098332703114, | |
| "median": 0.0004915725439786911 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5940084457397461, | |
| "mean": 4.8279449401888996e-05, | |
| "median": 3.9839310517209015e-08 | |
| } | |
| ], | |
| "bpw_layer": 16.0, | |
| "bpw_head": 16.0, | |
| "bpw_embed": 16.0, | |
| "vram_gb": 51.8809814453125 | |
| }, | |
| { | |
| "label": "2.50bpw-H5", | |
| "group": "EXL3", | |
| "ppl": 1.5697930692985753, | |
| "kld": 0.07011320441961288, | |
| "kld_median": 0.004001310560852289, | |
| "kld_p10": -2.0460726446458466e-09, | |
| "kld_p25": 1.936475655384129e-06, | |
| "kld_p75": 0.06180773675441742, | |
| "kld_p90": 0.18541844189167023, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.009831426665186882, | |
| "mean": 0.19685518741607666, | |
| "median": 0.1118646040558815 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10216876864433289, | |
| "mean": 0.1878684014081955, | |
| "median": 0.104058176279068 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1491546928882599, | |
| "mean": 0.1682659536600113, | |
| "median": 0.08561655133962631 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.1448366641998291, | |
| "mean": 0.11989079415798187, | |
| "median": 0.05045424401760101 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5940084457397461, | |
| "mean": 0.01097849477082491, | |
| "median": 6.721412773913471e-06 | |
| } | |
| ], | |
| "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": 1.5092496368231205, | |
| "kld": 0.03743031620979309, | |
| "kld_median": 0.001307627186179161, | |
| "kld_p10": -7.082661568347248e-09, | |
| "kld_p25": 7.289053201020579e-07, | |
| "kld_p75": 0.029712066054344177, | |
| "kld_p90": 0.09853020310401917, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.009831426665186882, | |
| "mean": 0.10391208529472351, | |
| "median": 0.059305980801582336 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10216876864433289, | |
| "mean": 0.1089409664273262, | |
| "median": 0.0600413903594017 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1491546928882599, | |
| "mean": 0.09427052736282349, | |
| "median": 0.04455190896987915 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.1448366641998291, | |
| "mean": 0.06253795325756073, | |
| "median": 0.023608867079019547 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5940084457397461, | |
| "mean": 0.0036357510834932327, | |
| "median": 1.7980112261284376e-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": 1.4789885178277211, | |
| "kld": 0.01853499747812748, | |
| "kld_median": 0.0005441498942673206, | |
| "kld_p10": -8.579068122571698e-09, | |
| "kld_p25": 4.0947213619801914e-07, | |
| "kld_p75": 0.013536326587200165, | |
| "kld_p90": 0.046271875500679016, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.009831426665186882, | |
| "mean": 0.06002768501639366, | |
| "median": 0.02889697626233101 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10216876864433289, | |
| "mean": 0.055736444890499115, | |
| "median": 0.027796383947134018 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1491546928882599, | |
| "mean": 0.047369033098220825, | |
| "median": 0.02040114998817444 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.1448366641998291, | |
| "mean": 0.028539668768644333, | |
| "median": 0.01042807474732399 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5940084457397461, | |
| "mean": 0.001770027563907206, | |
| "median": 1.1305555744911544e-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": 1.4660184947032182, | |
| "kld": 0.009837047196924686, | |
| "kld_median": 0.00026847864501178265, | |
| "kld_p10": -1.1636661412239846e-08, | |
| "kld_p25": 1.34371163085234e-07, | |
| "kld_p75": 0.007309188134968281, | |
| "kld_p90": 0.02560492977499962, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.009831426665186882, | |
| "mean": 0.03215811401605606, | |
| "median": 0.015666132792830467 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10216876864433289, | |
| "mean": 0.031469643115997314, | |
| "median": 0.016223572194576263 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1491546928882599, | |
| "mean": 0.025942282751202583, | |
| "median": 0.011609001085162163 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.1448366641998291, | |
| "mean": 0.014053885824978352, | |
| "median": 0.005612653214484453 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5940084457397461, | |
| "mean": 0.0006746386061422527, | |
| "median": 6.828307164141734e-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": 1.4553195376861408, | |
| "kld": 0.00347348116338253, | |
| "kld_median": 8.409866859437898e-05, | |
| "kld_p10": -8.652133232089909e-09, | |
| "kld_p25": 3.593997632833634e-08, | |
| "kld_p75": 0.0025442042388021946, | |
| "kld_p90": 0.00885797943919897, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.009831426665186882, | |
| "mean": 0.012675280682742596, | |
| "median": 0.0056492630392313 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10216876864433289, | |
| "mean": 0.01122499443590641, | |
| "median": 0.005648469552397728 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1491546928882599, | |
| "mean": 0.009140382520854473, | |
| "median": 0.003987093456089497 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.1448366641998291, | |
| "mean": 0.00494944816455245, | |
| "median": 0.0018848688341677189 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5940084457397461, | |
| "mean": 0.00020509578462224454, | |
| "median": 2.2256551801547175e-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": 1.4518262236078723, | |
| "kld": 0.0015066845808178186, | |
| "kld_median": 3.434611426200718e-05, | |
| "kld_p10": -1.6677040193258108e-08, | |
| "kld_p25": 9.329681915914989e-09, | |
| "kld_p75": 0.0011787005933001637, | |
| "kld_p90": 0.0038120318204164505, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.009831426665186882, | |
| "mean": 0.005867100786417723, | |
| "median": 0.0027884263545274734 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10216876864433289, | |
| "mean": 0.005056334659457207, | |
| "median": 0.0026827864348888397 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1491546928882599, | |
| "mean": 0.003987397998571396, | |
| "median": 0.0017997456016018987 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.1448366641998291, | |
| "mean": 0.00202021817676723, | |
| "median": 0.0008343607769347727 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5940084457397461, | |
| "mean": 7.586128049297258e-05, | |
| "median": 8.223299374776616e-08 | |
| } | |
| ], | |
| "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": 1.457104056220053, | |
| "kld": 0.005264023318886757, | |
| "kld_median": 0.00011304044164717197, | |
| "kld_p10": -8.80928396895797e-09, | |
| "kld_p25": 5.1164526837510493e-08, | |
| "kld_p75": 0.0042868610471487045, | |
| "kld_p90": 0.014257561415433884, | |
| "kld_buckets": [ | |
| { | |
| "conf_range": [ | |
| 0.0, | |
| 0.25 | |
| ], | |
| "share": 0.009831426665186882, | |
| "mean": 0.01879418082535267, | |
| "median": 0.011060066521167755 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.25, | |
| 0.5 | |
| ], | |
| "share": 0.10216876864433289, | |
| "mean": 0.017044372856616974, | |
| "median": 0.009706512093544006 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.5, | |
| 0.75 | |
| ], | |
| "share": 0.1491546928882599, | |
| "mean": 0.013917931355535984, | |
| "median": 0.006815092638134956 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.75, | |
| 0.95 | |
| ], | |
| "share": 0.1448366641998291, | |
| "mean": 0.007503218483179808, | |
| "median": 0.003147754818201065 | |
| }, | |
| { | |
| "conf_range": [ | |
| 0.95, | |
| 1.0 | |
| ], | |
| "share": 0.5940084457397461, | |
| "mean": 0.0002949148474726826, | |
| "median": 3.0352501312336244e-07 | |
| } | |
| ], | |
| "bpw_layer": 8.001953125, | |
| "bpw_head": 16.0, | |
| "bpw_embed": 16.0, | |
| "vram_gb": 28.45115613937378 | |
| } | |
| ] |