Skip to content

Commit 42e73e5

Browse files
author
kerem seyhan
committed
changed all defined short options to their corresponding long format in models.json.
1 parent 7cad0ef commit 42e73e5

File tree

1 file changed

+6
-6
lines changed

1 file changed

+6
-6
lines changed

models.json

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -5,15 +5,15 @@
55
"profiles": [
66
{
77
"name": "thinking",
8-
"command": "./llama-cli -hf Qwen/Qwen3-8B-GGUF:Q8_0 --jinja -fa --temp 0.6 --top-k 20 --top-p 0.95 --min-p 0 -c 40960 -n 32768 --no-context-shift",
8+
"command": "./llama-cli --model bartowski/Qwen_Qwen3-8B-GGUF/Qwen_Qwen3-8B-Q3_K_M.gguf --jinja --flash-attn --temp 0.6 --top-k 20 --top-p 0.95 --min-p 0 --ctx-size 40960 --predict 32768 --no-context-shift",
99
"references": [
1010
"https://qwen.readthedocs.io/en/latest/run_locally/llama.cpp.html#llama-cli",
1111
"https://huggingface.co/Qwen/Qwen3-235B-A22B#switching-between-thinking-and-non-thinking-mode"
1212
]
1313
},
1414
{
1515
"name": "non thinking",
16-
"command": "./llama-cli -hf Qwen/Qwen3-8B-GGUF:Q8_0 --jinja -fa --temp 0.7 --top-k 20 --top-p 0.8 --min-p 0 -c 40960 -n 32768 --no-context-shift",
16+
"command": "./llama-cli --model bartowski/Qwen_Qwen3-8B-GGUF/Qwen_Qwen3-8B-Q3_K_M.gguf --jinja --flash-attn --temp 0.7 --top-k 20 --top-p 0.8 --min-p 0 --ctx-size 40960 --predict 32768 --no-context-shift",
1717
"references": [
1818
"https://qwen.readthedocs.io/en/latest/run_locally/llama.cpp.html#llama-cli",
1919
"https://huggingface.co/Qwen/Qwen3-235B-A22B#switching-between-thinking-and-non-thinking-mode"
@@ -26,7 +26,7 @@
2626
"profiles": [
2727
{
2828
"name": "chat",
29-
"command": "./llama-cli --model unsloth-QwQ-32B-GGUF/QwQ-32B-Q4_K_M.gguf --ctx-size 16384 --temp 0.6 --repeat-penalty 1.1 --dry-multiplier 0.5 --min-p 0.01 --top-k 40 --top-p 0.95 --samplers \"top_k;top_p;min_p;temperature;dry;typ_p;xtc\"",
29+
"command": "./llama-cli --model unsloth-QwQ-32B-GGUF/QwQ-32B-Q4_K_M.gguf --ctx-size 32768 --temp 0.6 --repeat-penalty 1.1 --dry-multiplier 0.5 --min-p 0.01 --top-k 40 --top-p 0.95 --samplers \"top_k;top_p;min_p;temperature;dry;typ_p;xtc\"",
3030
"references": [
3131
"https://modelscope.cn/models/Qwen/QwQ-32B",
3232
"https://huggingface.co/Qwen/QwQ-32B",
@@ -40,7 +40,7 @@
4040
"profiles": [
4141
{
4242
"name": "chat",
43-
"command": "./llama-cli --model unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF/Llama-4-Scout-17B-16E-Instruct-UD-IQ2_XXS.gguf --ctx-size 16384 -ot \".ffn_.*_exps.=CPU\" --temp 0.6 --min-p 0.01 --top-p 0.9",
43+
"command": "./llama-cli --model unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF/Llama-4-Scout-17B-16E-Instruct-UD-IQ2_XXS.gguf --ctx-size 10485760 --temp 0.6 --min-p 0.01 --top-p 0.9",
4444
"references": [
4545
"https://www.llama.com/docs/llama-everywhere/running-meta-llama-on-linux/",
4646
"https://docs.unsloth.ai/basics/llama-4-how-to-run-and-fine-tune"
@@ -53,7 +53,7 @@
5353
"profiles": [
5454
{
5555
"name": "chat",
56-
"command": "./llama-cli --model bartowski/google_gemma-3-27b-it-qat-GGUF/gemma-3-27b-it-Q4_K_M.gguf --ctx-size 16384 --temp 1.0 --repeat-penalty 1.0 --min-p 0.01 --top-k 64 --top-p 0.95",
56+
"command": "./llama-cli --model bartowski/google_gemma-3-27b-it-qat-GGUF/gemma-3-27b-it-Q4_K_M.gguf --ctx-size 131072 --temp 1.0 --repeat-penalty 1.0 --min-p 0.01 --top-k 64 --top-p 0.95",
5757
"references": [
5858
"https://ollama.com/library/gemma3/blobs/3116c5225075",
5959
"https://docs.unsloth.ai/basics/gemma-3-how-to-run-and-fine-tune"
@@ -78,7 +78,7 @@
7878
"profiles": [
7979
{
8080
"name": "chat",
81-
"command": "./llama-cli --model bartowski/agentica-org_DeepCoder-14B-Preview-GGUF/agentica-org_DeepCoder-14B-Preview-Q6_K.gguf --ctx-size 64000 --temp 0.6 --top-p 0.95",
81+
"command": "./llama-cli --model bartowski/agentica-org_DeepCoder-14B-Preview-GGUF/agentica-org_DeepCoder-14B-Preview-Q6_K.gguf --ctx-size 131072 --temp 0.6 --top-p 0.95",
8282
"references": [
8383
"https://huggingface.co/agentica-org/DeepCoder-14B-Preview"
8484
],

0 commit comments

Comments
 (0)