mirror of
https://github.com/SerTimBerrners-Lee/talkis.git
synced 2026-07-09 17:29:15 +00:00
fix(local): use bartowski single-file Qwen GGUF URLs (7B was 404)
The official Qwen2.5-7B-Instruct-GGUF q4_k_m is split into 2 parts (404 for the single-file name we used). Switch both 3B and 7B to bartowski's single-file Q4_K_M GGUFs, both verified to return 200.
This commit is contained in:
parent
a69b993694
commit
fe81d2e7e8
1 changed files with 4 additions and 4 deletions
|
|
@ -31,16 +31,16 @@ struct LlmModelInfo {
|
|||
static LLM_CATALOG: &[LlmModelInfo] = &[
|
||||
LlmModelInfo {
|
||||
id: "qwen2.5-3b-instruct-q4",
|
||||
file_name: "qwen2.5-3b-instruct-q4_k_m.gguf",
|
||||
url: "https://huggingface.co/Qwen/Qwen2.5-3B-Instruct-GGUF/resolve/main/qwen2.5-3b-instruct-q4_k_m.gguf",
|
||||
file_name: "Qwen2.5-3B-Instruct-Q4_K_M.gguf",
|
||||
url: "https://huggingface.co/bartowski/Qwen2.5-3B-Instruct-GGUF/resolve/main/Qwen2.5-3B-Instruct-Q4_K_M.gguf",
|
||||
label: "Qwen2.5 3B Instruct",
|
||||
size_label: "2.0 ГБ",
|
||||
min_ram_gb: 8,
|
||||
},
|
||||
LlmModelInfo {
|
||||
id: "qwen2.5-7b-instruct-q4",
|
||||
file_name: "qwen2.5-7b-instruct-q4_k_m.gguf",
|
||||
url: "https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-GGUF/resolve/main/qwen2.5-7b-instruct-q4_k_m.gguf",
|
||||
file_name: "Qwen2.5-7B-Instruct-Q4_K_M.gguf",
|
||||
url: "https://huggingface.co/bartowski/Qwen2.5-7B-Instruct-GGUF/resolve/main/Qwen2.5-7B-Instruct-Q4_K_M.gguf",
|
||||
label: "Qwen2.5 7B Instruct",
|
||||
size_label: "4.7 ГБ",
|
||||
min_ram_gb: 16,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue