|
|
| Line 110: |
Line 110: |
|
| |
|
| = Build environment = | | = Build environment = |
|
| |
| == hf (model management) ==
| |
|
| |
|
| |
| {| class="wikitable"
| |
| ! Purpose || Command
| |
| |-
| |
| | cache management ||
| |
| <syntaxhighlight lang="bash">
| |
| hf cache list
| |
| hf cache rm <model id>
| |
| hf cache prune
| |
| </syntaxhighlight>
| |
| |-
| |
| | fix WiFi problem ||
| |
| <syntaxhighlight lang="bash">
| |
| HF_XET_FIXED_DOWNLOAD_CONCURRENCY=10 hf download "unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF" --include "*UD-Q4_K_XL*"
| |
| HF_XET_FIXED_DOWNLOAD_CONCURRENCY=10 hf download "unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF" --include "*UD-Q4_K_XL*"
| |
| </syntaxhighlight>
| |
| |-
| |
| | search ||
| |
| <syntaxhighlight lang="bash">
| |
| # search by population
| |
| hf models ls --search "Muse-Glimmer" --apps llama.cpp --expand "downloads,likes,createdAt,lastModified" --sort downloads --no-truncate --limit 25
| |
| # search for latest publish
| |
| hf models ls --search "Muse-Glimmer" --apps llama.cpp --expand "downloads,likes,createdAt,lastModified" --sort created_at --no-truncate --limit 25
| |
| # search for latest tunning
| |
| hf models ls --search "Muse-Glimmer" --apps llama.cpp --expand "downloads,likes,createdAt,lastModified" --sort last_modified --no-truncate --limit 25
| |
| </syntaxhighlight>
| |
| |-
| |
| | optimize Qwen3-Coder ||
| |
| <syntaxhighlight lang="bash">
| |
| hf models ls --search "coder" --apps llama.cpp --sort downloads --limit 1 --format json | jq .
| |
| hf models ls -h "unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF"
| |
| hf download "unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF" --include "*UD-Q4_K_XL*"
| |
| </syntaxhighlight>
| |
| |-
| |
| | optimize gemma-4-E4B ||
| |
| <syntaxhighlight lang="bash">
| |
| hf models ls -h unsloth/gemma-4-E4B-it-qat-GGUF
| |
| hf download unsloth/gemma-4-E4B-it-qat-GGUF --include "*UD-Q4_K_XL*"
| |
| hf download unsloth/gemma-4-E4B-it-qat-GGUF --include "mmproj-BF16.gguf"
| |
| hf download unsloth/gemma-4-E4B-it-qat-GGUF --include "mtp-gemma-4-E4B-it.gguf"
| |
| </syntaxhighlight>
| |
| |-
| |
| | optimize gemma-4-12B ||
| |
| <syntaxhighlight lang="bash">
| |
| hf models ls -h unsloth/gemma-4-12B-it-qat-GGUF
| |
| hf download unsloth/gemma-4-12B-it-qat-GGUF --include "*UD-Q4_K_XL*"
| |
| hf download unsloth/gemma-4-12B-it-qat-GGUF --include "mmproj-BF16.gguf"
| |
| hf download unsloth/gemma-4-12B-it-qat-GGUF --include "mtp-gemma-4-12B-it.gguf"
| |
| </syntaxhighlight>
| |
| |-
| |
| | optimize Muse Glimmer ||
| |
| <syntaxhighlight lang="bash">
| |
| hf models ls -h unsloth/Muse-Glimmer-30B-GGUF
| |
| hf download unsloth/Muse-Glimmer-30B-GGUF --include "*UD-Q4_K_XL*"
| |
| hf download unsloth/Muse-Glimmer-30B-GGUF --include "*UD-Q5_K_XL*"
| |
| hf download unsloth/Muse-Glimmer-30B-GGUF --include "*UD-Q6_K_XL*"
| |
| hf download unsloth/Muse-Glimmer-30B-GGUF --include "dflash-kquant.gguf"
| |
| hf download unsloth/Muse-Glimmer-30B-GGUF --include "mmproj-kquant.gguf"
| |
| </syntaxhighlight>
| |
| |-
| |
| | ||
| |
| <syntaxhighlight lang="bash">
| |
| tree ~/.cache/huggingface/hub/models--unsloth--Devstral-Small-2-24B-Instruct-2512-GGUF/snapshots
| |
| tree ~/.cache/huggingface/hub/models--unsloth--Qwen3-Coder-30B-A3B-Instruct-GGUF/snapshots
| |
| </syntaxhighlight>
| |
| |}
| |
|
| |
|
| == Ubuntu == | | == Ubuntu == |
