Update to v2

.gitattributes

@@ -33,13 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-ggml-model-q2_K.bin filter=lfs diff=lfs merge=lfs -text
-ggml-model-q3_K.bin filter=lfs diff=lfs merge=lfs -text
-ggml-model-q4_1.bin filter=lfs diff=lfs merge=lfs -text
-ggml-model-q5_1.bin filter=lfs diff=lfs merge=lfs -text
-ggml-model-q8_0.bin filter=lfs diff=lfs merge=lfs -text
-ggml-model-q2_K.gguf filter=lfs diff=lfs merge=lfs -text
-ggml-model-q3_K.gguf filter=lfs diff=lfs merge=lfs -text
-ggml-model-q4_K.gguf filter=lfs diff=lfs merge=lfs -text
-ggml-model-q5_K.gguf filter=lfs diff=lfs merge=lfs -text
-ggml-model-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text
+model-q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+model-q3_K.gguf filter=lfs diff=lfs merge=lfs -text
+model-q4_K.gguf filter=lfs diff=lfs merge=lfs -text
+model-q5_K.gguf filter=lfs diff=lfs merge=lfs -text
+model-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -15,16 +15,23 @@ license: llama2
 
 Llama.cpp compatible versions of an original [7B model](https://huggingface.co/IlyaGusev/saiga2_7b_lora).
 
-* Download one of the versions, for example `ggml-model-q4_K.gguf`.
+* Download one of the versions, for example `model-q4_K.gguf`.
+```
+wget https://huggingface.co/IlyaGusev/saiga2_7b_gguf/resolve/main/model-q4_K.gguf
+```
+
 * Download [interact_llamacpp.py](https://raw.githubusercontent.com/IlyaGusev/rulm/master/self_instruct/src/interact_llamacpp.py)
+```
+wget https://raw.githubusercontent.com/IlyaGusev/rulm/master/self_instruct/src/interact_llamacpp.py
+```
 
 How to run:
 ```
 sudo apt-get install git-lfs
 pip install llama-cpp-python fire
 
-python3 interact_llamacpp.py ggml-model-q4_K.gguf
+python3 interact_llamacpp.py model-q4_K.gguf
 ```
 
 System requirements:
-* 10GB RAM for q8_0 and less for smaller quantizations
+* 10GB RAM for q8_0 and less for smaller quantizations

ggml-model-q2_K.gguf → model-q2_K.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5e836e165a30324d59a8c0628c6482019fad3ccc859559f5140960ad80a8a0
+oid sha256:ecdb8ac229f6cdc3f21d5a3e95dcd26f31c355b727299e96b44ab7a7dbc34fb4
 size 2825940544

ggml-model-q3_K.gguf → model-q3_K.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:863334afda6984017dd4e867179cc3e5880e655c71bddabe89a3e7f4065f6f03
+oid sha256:04ec17b11219d55186d69deae515ec909ea54ecd5918b803f8deabd7a575396c
 size 3298004544

ggml-model-q4_K.gguf → model-q4_K.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:279b2015313bae92d58575d1bd5b8655bbd89ae4df5899a1ba6f836bb4a18320
+oid sha256:b6d9ab608346c90e70eae6ab086524550c7ff5d5a34e6eb98b5b0531ef62b991
 size 4081004096

ggml-model-q5_K.gguf → model-q5_K.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c505438c61806b10b498623c8094de0ba0e18db23d57b9a3c9f5910efbbe767
+oid sha256:149862753771f3a096e05b3732c520d37d8a2b099b795a4434b813fe989d1f58
 size 4783156800

ggml-model-q8_0.gguf → model-q8_0.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e1566dea76b28e20fcf7f240abdd6239ccf33e81556131ffd4a580a2c45d472
+oid sha256:1c51054fa221c692ba2cee0ebfa63e87c1fed2abdf8608bb820c5c1b58c5c22c
 size 7161089600