Add Qwen GSQ-RCO Beta 1 profile
This commit is contained in:
@@ -15,6 +15,7 @@ DEFAULT_REASONING_EFFORT=off
|
||||
|
||||
FAST_MODEL_FILE=qwen-mix/Qwen3.8-27B-IQ4-MIX.gguf
|
||||
MEDIUM_MODEL_FILE=qwen-pure/qwen3.8-27b-IQ4_XS-pure.gguf
|
||||
BETA1_MODEL_FILE=qwen3.8-27b-gsq-rco-test/Qwen3.8-27B-GSQ-RCO-IQ3_XXS-mtp.gguf
|
||||
LARGE_MODEL_FILE=qwen-pure/qwen3.8-27b-IQ4_XS-pure.gguf
|
||||
ULTRA_MODEL_FILE=qwen-pure/qwen3.8-27b-IQ4_XS-pure.gguf
|
||||
UNCENSORED_MODEL_FILE=qwen3.8-27b-abliterated/Qwen3.8-27B-ABLITERATED-Q4_K_M.gguf
|
||||
@@ -27,6 +28,9 @@ FAST_UBATCH_SIZE=32
|
||||
MEDIUM_CONTEXT=160000
|
||||
MEDIUM_BATCH_SIZE=2048
|
||||
MEDIUM_UBATCH_SIZE=128
|
||||
BETA1_CONTEXT=192000
|
||||
BETA1_BATCH_SIZE=2048
|
||||
BETA1_UBATCH_SIZE=128
|
||||
LARGE_CONTEXT=192000
|
||||
LARGE_BATCH_SIZE=2048
|
||||
LARGE_UBATCH_SIZE=128
|
||||
@@ -39,6 +43,7 @@ UNCENSORED_UBATCH_SIZE=128
|
||||
FAST_GPU_DEVICES=GPU-8ad38c6c-5a01-9d8e-1dfa-ed662ad78fbe,GPU-4834d9d7-5b61-3004-1fb3-4ae49d482d4b
|
||||
MEDIUM_GPU_DEVICES=GPU-8ad38c6c-5a01-9d8e-1dfa-ed662ad78fbe,GPU-4834d9d7-5b61-3004-1fb3-4ae49d482d4b
|
||||
MEDIUM_TENSOR_SPLIT=85,15
|
||||
BETA1_GPU_DEVICES=GPU-8ad38c6c-5a01-9d8e-1dfa-ed662ad78fbe,GPU-4834d9d7-5b61-3004-1fb3-4ae49d482d4b
|
||||
LARGE_GPU_DEVICES=GPU-8ad38c6c-5a01-9d8e-1dfa-ed662ad78fbe,GPU-4834d9d7-5b61-3004-1fb3-4ae49d482d4b
|
||||
LARGE_TENSOR_SPLIT=86,14
|
||||
ULTRA_GPU_DEVICES=GPU-8ad38c6c-5a01-9d8e-1dfa-ed662ad78fbe,GPU-4834d9d7-5b61-3004-1fb3-4ae49d482d4b
|
||||
@@ -51,6 +56,7 @@ LLAMA_THREADS_BATCH=6
|
||||
FAST_PARALLEL_SLOTS=1
|
||||
LLAMA_CACHE_RAM_MIB=32768
|
||||
MEDIUM_PARALLEL_SLOTS=1
|
||||
BETA1_PARALLEL_SLOTS=1
|
||||
LARGE_PARALLEL_SLOTS=1
|
||||
ULTRA_PARALLEL_SLOTS=1
|
||||
UNCENSORED_PARALLEL_SLOTS=1
|
||||
|
||||
Reference in New Issue
Block a user