update readme with IQ4_K and IQ5_KS
Browse files
README.md
CHANGED
@@ -351,14 +351,12 @@ numactl -N 0 -m 0 \
|
|
351 |
If you want to disable thinking, add `/nothink` (correct, no underscore) at the *end* of your prompt.
|
352 |
|
353 |
```bash
|
354 |
-
# Clone and checkout experimental PR
|
355 |
$ git clone https://github.com/ikawrakow/ik_llama.cpp
|
356 |
$ cd ik_llama.cpp
|
357 |
$ git remote add Thireus https://github.com/Thireus/ik_llama.cpp.git
|
358 |
$ git fetch Thireus
|
359 |
-
$ git checkout glm-4.5-
|
360 |
-
# If glm-4.5-clean is ready, use it instead of -testing
|
361 |
-
# $ git checkout glm-4.5-clean
|
362 |
|
363 |
# Build for hybrid CPU+CUDA
|
364 |
$ cmake -B build -DCMAKE_BUILD_TYPE=Release -DGGML_CUDA=ON -DGGML_BLAS=OFF -DGGML_SCHED_MAX_COPIES=1
|
|
|
351 |
If you want to disable thinking, add `/nothink` (correct, no underscore) at the *end* of your prompt.
|
352 |
|
353 |
```bash
|
354 |
+
# Clone and checkout experimental PR (hopefully merged into main soon)
|
355 |
$ git clone https://github.com/ikawrakow/ik_llama.cpp
|
356 |
$ cd ik_llama.cpp
|
357 |
$ git remote add Thireus https://github.com/Thireus/ik_llama.cpp.git
|
358 |
$ git fetch Thireus
|
359 |
+
$ git checkout glm-4.5-clean
|
|
|
|
|
360 |
|
361 |
# Build for hybrid CPU+CUDA
|
362 |
$ cmake -B build -DCMAKE_BUILD_TYPE=Release -DGGML_CUDA=ON -DGGML_BLAS=OFF -DGGML_SCHED_MAX_COPIES=1
|