LM/hf: Difference between revisions

From Fundamental Ramen
< LM
Jump to navigation Jump to search
(Created page with "{| 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*" </syntaxhi...")
 
 
(17 intermediate revisions by the same user not shown)
Line 1: Line 1:
== Quick references ==
{| class="wikitable"
{| class="wikitable"
! Purpose || Command
! Purpose || Command
Line 15: Line 17:
</syntaxhighlight>
</syntaxhighlight>
|-
|-
| search ||
| search for vLLM ||
<syntaxhighlight lang="bash">
<syntaxhighlight lang="bash">
# search by population
# search by population
hf models ls --search "Muse-Glimmer" --apps llama.cpp --expand "downloads,likes,createdAt,lastModified" --sort downloads --no-truncate --limit 25
hf models ls --search "Qwen3.8 27B MixedINT4 AutoRound" --apps vllm --expand "downloads,likes,createdAt,lastModified" --sort downloads --no-truncate --no-gated --limit 10
# search by population
hf models ls --search "Qwen3.8 27B INT4 AutoRound" --apps vllm --expand "downloads,likes,createdAt,lastModified" --sort downloads --no-truncate --no-gated --limit 10
# search for latest publish
# 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
hf models ls --search "Qwen3.8 27B INT4 AutoRound" --apps vllm --expand "downloads,likes,createdAt,lastModified" --sort created_at --no-truncate --no-gated --limit 10
# search for latest tunning
# 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
hf models ls --search "Qwen3.8 27B INT4 AutoRound" --apps vllm --expand "downloads,likes,createdAt,lastModified" --sort last_modified --no-truncate --no-gated --limit 10
</syntaxhighlight>
</syntaxhighlight>
|-
|-
| optimize Qwen3-Coder ||
| search for llama.cpp ||
<syntaxhighlight lang="bash">
<syntaxhighlight lang="bash">
hf models ls --search "coder" --apps llama.cpp --sort downloads --limit 1 --format json | jq .
# search by population
hf models ls -h "unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF"
hf models ls --search "Muse-Glimmer" --apps llama.cpp --expand "downloads,likes,createdAt,lastModified" --sort downloads --no-truncate --no-gated --limit 10
hf download "unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF" --include "*UD-Q4_K_XL*"
# search for latest publish
hf models ls --search "Muse-Glimmer" --apps llama.cpp --expand "downloads,likes,createdAt,lastModified" --sort created_at --no-truncate --no-gated --limit 10
# search for latest tunning
hf models ls --search "Muse-Glimmer" --apps llama.cpp --expand "downloads,likes,createdAt,lastModified" --sort last_modified --no-truncate --no-gated --limit 10
</syntaxhighlight>
</syntaxhighlight>
|-
|-
| optimize gemma-4-E4B ||
| search for OpenVINO ||
<syntaxhighlight lang="bash">
<syntaxhighlight lang="bash">
hf models ls -h unsloth/gemma-4-E4B-it-qat-GGUF
# search OpenVINO format
hf download unsloth/gemma-4-E4B-it-qat-GGUF --include "*UD-Q4_K_XL*"
hf models ls --search "Qwen3.8" --filter openvino --expand "downloads,likes,createdAt,lastModified" --sort downloads --no-truncate --no-gated --limit 10
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>
</syntaxhighlight>
|-
|-
Line 64: Line 61:
</syntaxhighlight>
</syntaxhighlight>
|}
|}
== Install ==
<syntaxhighlight lang="bash">
sudo apt update
sudo apt install pipx -y
pipx ensurepath
pipx install "huggingface_hub[cli]"
</syntaxhighlight>
== Environment Variables for hf ==
* https://huggingface.co/docs/huggingface_hub/package_reference/environment_variables

Latest revision as of 07:17, 24 September 2026

Quick references

Purpose Command
cache management 
hf cache list
hf cache rm <model id>
hf cache prune
fix WiFi problem 
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*"
search for vLLM 
# search by population
hf models ls --search "Qwen3.8 27B MixedINT4 AutoRound" --apps vllm --expand "downloads,likes,createdAt,lastModified" --sort downloads --no-truncate --no-gated --limit 10
# search by population
hf models ls --search "Qwen3.8 27B INT4 AutoRound" --apps vllm --expand "downloads,likes,createdAt,lastModified" --sort downloads --no-truncate --no-gated --limit 10
# search for latest publish
hf models ls --search "Qwen3.8 27B INT4 AutoRound" --apps vllm --expand "downloads,likes,createdAt,lastModified" --sort created_at --no-truncate --no-gated --limit 10
# search for latest tunning
hf models ls --search "Qwen3.8 27B INT4 AutoRound" --apps vllm --expand "downloads,likes,createdAt,lastModified" --sort last_modified --no-truncate --no-gated --limit 10
search for llama.cpp 
# search by population
hf models ls --search "Muse-Glimmer" --apps llama.cpp --expand "downloads,likes,createdAt,lastModified" --sort downloads --no-truncate --no-gated --limit 10
# search for latest publish
hf models ls --search "Muse-Glimmer" --apps llama.cpp --expand "downloads,likes,createdAt,lastModified" --sort created_at --no-truncate --no-gated --limit 10
# search for latest tunning
hf models ls --search "Muse-Glimmer" --apps llama.cpp --expand "downloads,likes,createdAt,lastModified" --sort last_modified --no-truncate --no-gated --limit 10
search for OpenVINO 
# search OpenVINO format
hf models ls --search "Qwen3.8" --filter openvino --expand "downloads,likes,createdAt,lastModified" --sort downloads --no-truncate --no-gated --limit 10
optimize Muse Glimmer 
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"

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

Install

sudo apt update
sudo apt install pipx -y
pipx ensurepath
pipx install "huggingface_hub[cli]"

Environment Variables for hf

Retrieved from "https://wiki.fundamental-ramen.com/index.php?title=LM/hf&oldid=3625"