sleepy/llama.cpp
1
0
Fork 0
Code Issues 8 Pull Requests Actions 168 Packages Projects Releases Wiki Activity

misc : prefer ggml-org models in docs and examples (#20827)

Browse Source 
* misc : prefer ggml-org models in docs and examples

Prefer referring to known-good quantizations under ggml-org rather than
3rd-party uploaders.

* remove accidentally committed file
This commit is contained in:
ddh0
2026-03-21 16:00:26 -05:00
committed by GitHub
parent 990e4d9698
commit 3306dbaef7
7 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/README.md
+1 -1
View File
@@ -100,7 +100,7 @@ For the full list of features, please refer to [server's changelog](https://gith
| `-m, --model FNAME` | model path to load<br/>(env: LLAMA_ARG_MODEL) |
| `-mu, --model-url MODEL_URL` | model download url (default: unused)<br/>(env: LLAMA_ARG_MODEL_URL) |
| `-dr, --docker-repo [<repo>/]<model>[:quant]` | Docker Hub model repository. repo is optional, default to ai/. quant is optional, default to :latest.<br/>example: gemma3<br/>(default: unused)<br/>(env: LLAMA_ARG_DOCKER_REPO) |
| `-hf, -hfr, --hf-repo <user>/<model>[:quant]` | Hugging Face model repository; quant is optional, case-insensitive, default to Q4_K_M, or falls back to the first file in the repo if Q4_K_M doesn't exist.<br/>mmproj is also downloaded automatically if available. to disable, add --no-mmproj<br/>example: unsloth/phi-4-GGUF:q4_k_m<br/>(default: unused)<br/>(env: LLAMA_ARG_HF_REPO) |
| `-hf, -hfr, --hf-repo <user>/<model>[:quant]` | Hugging Face model repository; quant is optional, case-insensitive, default to Q4_K_M, or falls back to the first file in the repo if Q4_K_M doesn't exist.<br/>mmproj is also downloaded automatically if available. to disable, add --no-mmproj<br/>example: ggml-org/GLM-4.7-Flash-GGUF:Q4_K_M<br/>(default: unused)<br/>(env: LLAMA_ARG_HF_REPO) |
| `-hfd, -hfrd, --hf-repo-draft <user>/<model>[:quant]` | Same as --hf-repo, but for the draft model (default: unused)<br/>(env: LLAMA_ARG_HFD_REPO) |
| `-hff, --hf-file FILE` | Hugging Face model file. If specified, it will override the quant in --hf-repo (default: unused)<br/>(env: LLAMA_ARG_HF_FILE) |
| `-hfv, -hfrv, --hf-repo-v <user>/<model>[:quant]` | Hugging Face model repository for the vocoder model (default: unused)<br/>(env: LLAMA_ARG_HF_REPO_V) |
tools/server/webui/src/lib/constants/settings-config.ts
+1 -1
View File
@@ -127,7 +127,7 @@ export const SETTING_CONFIG_INFO: Record<string, string> = {
fullHeightCodeBlocks:
'Always display code blocks at their full natural height, overriding any height limits.',
showRawModelNames:
'Display full raw model identifiers (e.g. "unsloth/Qwen3.5-27B-GGUF:BF16") instead of parsed names with badges.',
'Display full raw model identifiers (e.g. "ggml-org/GLM-4.7-Flash-GGUF:Q8_0") instead of parsed names with badges.',
mcpServers:
'Configure MCP servers as a JSON list. Use the form in the MCP Client settings section to edit.',
mcpServerUsageStats:
tools/server/webui/src/lib/stores/models.svelte.ts
+1 -1
View File
@@ -457,7 +457,7 @@ class ModelsStore {
/**
* Select a model by its model name (used for syncing with conversation model)
* @param modelName - Model name to select (e.g., "unsloth/gemma-3-12b-it-GGUF:latest")
* @param modelName - Model name to select (e.g., "ggml-org/GLM-4.7-Flash-GGUF")
*/
selectModelByName(modelName: string): void {
const option = this.models.find((model) => model.model === modelName);