Upload folder using huggingface_hub
Browse files- .gitattributes +6 -0
- README.md +17 -0
- granite-3.1-8b-instruct-abliterated.f16.gguf +3 -0
- granite-3.1-8b-instruct-abliterated.q5_k.gguf +3 -0
- granite-3.1-8b-instruct-abliterated.q6_k.gguf +3 -0
- granite-3.1-8b-instruct-abliterated.q8_0.gguf +3 -0
- granite-3.1-8b-instruct-abliterated.q8_p.gguf +3 -0
- granite-3.1-8b-instruct-abliterated.q8q4.gguf +3 -0
- granite-3.1-8b-instruct-abliterated/README.md +26 -0
.gitattributes
CHANGED
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
granite-3.1-8b-instruct-abliterated.f16.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
granite-3.1-8b-instruct-abliterated.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
granite-3.1-8b-instruct-abliterated.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
granite-3.1-8b-instruct-abliterated.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
granite-3.1-8b-instruct-abliterated.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
granite-3.1-8b-instruct-abliterated.q8q4.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
license: mit
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
---
|
8 |
+
|
9 |
+
My own (ZeroWw) quantizations.
|
10 |
+
output and embed tensors quantized to f16.
|
11 |
+
all other tensors quantized to q5_k or q6_k.
|
12 |
+
|
13 |
+
Result:
|
14 |
+
both f16.q6 and f16.q5 are smaller than q8_0 standard quantization
|
15 |
+
and they perform as well as the pure f16.
|
16 |
+
|
17 |
+
Updated on: Sat Jan 11, 00:38:07
|
granite-3.1-8b-instruct-abliterated.f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a10f4aced2b512224f071897304484b952b224c3ff579d43e0b4130ced2b5359
|
3 |
+
size 16344105696
|
granite-3.1-8b-instruct-abliterated.q5_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3345e9f82f31feccb7aa307c1af33c886674ff1924ffc7125e655e09b87e0ec2
|
3 |
+
size 6034965216
|
granite-3.1-8b-instruct-abliterated.q6_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63b3ac2f4199c6cffda823fc9fbbd1e77069a73e3f8f814495b8ce876ce38316
|
3 |
+
size 6942966496
|
granite-3.1-8b-instruct-abliterated.q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcb46da1b94151dca4a5189d41ef52a3d2a643c077d076e1074a9c312c5d5715
|
3 |
+
size 8873001696
|
granite-3.1-8b-instruct-abliterated.q8_p.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fb2e4e56844796dd3da972fbd8f84143922ba4ac36f6378a93081af1a731279
|
3 |
+
size 8684246496
|
granite-3.1-8b-instruct-abliterated.q8q4.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e94ad5ffaaaa501bbb3dc670b820bde99a41a7b743e5bdfd16f76e566294ca1
|
3 |
+
size 4991620576
|
granite-3.1-8b-instruct-abliterated/README.md
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
pipeline_tag: text-generation
|
3 |
+
inference: false
|
4 |
+
license: apache-2.0
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- language
|
8 |
+
- granite-3.1
|
9 |
+
- abliterated
|
10 |
+
- uncensored
|
11 |
+
base_model:
|
12 |
+
- ibm-granite/granite-3.1-8b-instruct
|
13 |
+
---
|
14 |
+
|
15 |
+
# huihui-ai/granite-3.1-8b-instruct-abliterated
|
16 |
+
|
17 |
+
|
18 |
+
This is an uncensored version of [ibm-granite/granite-3.1-8b-instruct](https://huggingface.co/ibm-granite/granite-3.1-8b-instruct) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
|
19 |
+
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
|
20 |
+
|
21 |
+
## Use with ollama
|
22 |
+
|
23 |
+
You can use [huihui_ai/granite3.1-dense-abliterated](https://ollama.com/huihui_ai/granite3.1-dense-abliterated) directly,
|
24 |
+
```
|
25 |
+
ollama run huihui_ai/granite3.1-dense-abliterated
|
26 |
+
```
|