Avoid printing incomplete bytes
#1
by
fikavec
- opened
- README.md +4 -4
- ggml-model-q4_1.bin +2 -2
- ggml-model-q5_1.bin +1 -1
- ggml-model-q8_0.bin +2 -2
README.md
CHANGED
@@ -6,22 +6,22 @@ datasets:
|
|
6 |
language:
|
7 |
- ru
|
8 |
inference: false
|
9 |
-
pipeline_tag:
|
10 |
---
|
11 |
|
12 |
Llama.cpp compatible versions of an original [13B model](https://huggingface.co/IlyaGusev/saiga_13b_lora).
|
13 |
|
14 |
* Download one of the versions, for example `ggml-model-q4_1.bin`.
|
15 |
-
* Download [
|
16 |
|
17 |
How to run:
|
18 |
```
|
19 |
sudo apt-get install git-lfs
|
20 |
pip install llama-cpp-python fire
|
21 |
|
22 |
-
python3
|
23 |
```
|
24 |
|
25 |
System requirements:
|
26 |
* 18GB RAM for q8_0
|
27 |
-
* 13GB RAM for q4_1
|
|
|
6 |
language:
|
7 |
- ru
|
8 |
inference: false
|
9 |
+
pipeline_tag: text2text-generation
|
10 |
---
|
11 |
|
12 |
Llama.cpp compatible versions of an original [13B model](https://huggingface.co/IlyaGusev/saiga_13b_lora).
|
13 |
|
14 |
* Download one of the versions, for example `ggml-model-q4_1.bin`.
|
15 |
+
* Download [interact_saiga_llamacpp.py](https://raw.githubusercontent.com/IlyaGusev/rulm/master/self_instruct/src/infer_saiga_llamacpp.py)
|
16 |
|
17 |
How to run:
|
18 |
```
|
19 |
sudo apt-get install git-lfs
|
20 |
pip install llama-cpp-python fire
|
21 |
|
22 |
+
python3 interact_saiga_llamacpp.py ggml-model-q4_1.bin
|
23 |
```
|
24 |
|
25 |
System requirements:
|
26 |
* 18GB RAM for q8_0
|
27 |
+
* 13GB RAM for q4_1
|
ggml-model-q4_1.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9fed0b0e45e8731d0e1a0c8ed5b36f83951887805147a2012b327fe9aa7a5b9
|
3 |
+
size 9763701888
|
ggml-model-q5_1.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9763701888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0098b1bab55b796bb9a1d596241f266205220738f3a9a9064990e44b78b2453
|
3 |
size 9763701888
|
ggml-model-q8_0.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b2bc1ee6a05625f78af12f0011ead209a049f986395c1b08eadcb9abd00f992
|
3 |
+
size 14644495488
|