ZeroWw commited on
Commit
6c799e2
1 Parent(s): c4bb370

Upload folder using huggingface_hub

Browse files
.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
+ Llama-3.2-3B-Instruct-abliterated.f16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Llama-3.2-3B-Instruct-abliterated.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Llama-3.2-3B-Instruct-abliterated.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Llama-3.2-3B-Instruct-abliterated.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Llama-3.2-3B-Instruct-abliterated.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Llama-3.2-3B-Instruct-abliterated.q8q4.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.2-3B-Instruct-abliterated.f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45806f8222030d552f33f34ad9691bed830f13a516c46187211a9ffa356faf6e
3
+ size 7221692896
Llama-3.2-3B-Instruct-abliterated.q5_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68d27e9a624030703b3b6e348588a5a96934ede26f9c7fc9dd26ee9bbaf54de8
3
+ size 3574958560
Llama-3.2-3B-Instruct-abliterated.q6_k.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e06922a36e5434cb71f0fc632fcdd5609783cc477bbc3217b8cbd5d3ce2ffbde
3
+ size 3896658400
Llama-3.2-3B-Instruct-abliterated.q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b8a0c906b54a689087a4b05b8172cac9ba80d702c8f9f1ac334966bfeade93
3
+ size 4579281376
Llama-3.2-3B-Instruct-abliterated.q8_p.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c62911a626c1abd577a8f58a73fb6a32d32840605b287a1ebf1c1453eaacf5ce
3
+ size 3840526816
Llama-3.2-3B-Instruct-abliterated.q8q4.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5dfa5c56e147c9fa495359e5783400e205fbc01995c919dc265a2cf1645d664
3
+ size 2533427680
Llama-3.2-3B-Instruct-abliterated/README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: llama3.2
4
+ base_model: meta-llama/Llama-3.2-3B-Instruct
5
+ tags:
6
+ - abliterated
7
+ - uncensored
8
+ ---
9
+
10
+ # 🦙 Llama-3.2-3B-Instruct-abliterated
11
+
12
+
13
+
14
+ This is an uncensored version of Llama 3.2 3B Instruct created with abliteration (see [this article](https://huggingface.co/blog/mlabonne/abliteration) to know more about it).
15
+
16
+ Special thanks to [@FailSpy](https://huggingface.co/failspy) for the original code and technique. Please follow him if you're interested in abliterated models.
17
+
18
+ ## Evaluations
19
+ The following data has been re-evaluated and calculated as the average for each test.
20
+
21
+ | Benchmark | Llama-3.2-3B-Instruct | Llama-3.2-3B-Instruct-abliterated |
22
+ |-------------|-----------------------|-----------------------------------|
23
+ | IF_Eval | 76.55 | **76.76** |
24
+ | MMLU Pro | 27.88 | **28.00** |
25
+ | TruthfulQA | 50.55 | **50.73** |
26
+ | BBH | 41.81 | **41.86** |
27
+ | GPQA | 28.39 | **28.41** |
28
+
29
+ The script used for evaluation can be found inside this repository under /eval.sh, or click [here](https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated/blob/main/eval.sh)
Llama-3.2-3B-Instruct-abliterated/USE_POLICY.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ **Llama 3.2** **Acceptable Use Policy**
2
+
3
+ Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use Policy (“**Policy**”). The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).
4
+
5
+ **Prohibited Uses**
6
+
7
+ We want everyone to use Llama 3.2 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.2 to:
8
+
9
+
10
+
11
+ 1. Violate the law or others’ rights, including to:
12
+ 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
13
+ 1. Violence or terrorism
14
+ 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
15
+ 3. Human trafficking, exploitation, and sexual violence
16
+ 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
17
+ 5. Sexual solicitation
18
+ 6. Any other criminal activity
19
+ 1. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
20
+ 2. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
21
+ 3. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
22
+ 4. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law
23
+ 5. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
24
+ 6. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
25
+ 7. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta 
26
+ 2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.2 related to the following:
27
+ 8. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997
28
+ 9. Guns and illegal weapons (including weapon development)
29
+ 10. Illegal drugs and regulated/controlled substances
30
+ 11. Operation of critical infrastructure, transportation technologies, or heavy machinery
31
+ 12. Self-harm or harm to others, including suicide, cutting, and eating disorders
32
+ 13. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
33
+ 3. Intentionally deceive or mislead others, including use of Llama 3.2 related to the following:
34
+ 14. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
35
+ 15. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
36
+ 16. Generating, promoting, or further distributing spam
37
+ 17. Impersonating another individual without consent, authorization, or legal right
38
+ 18. Representing that the use of Llama 3.2 or outputs are human-generated
39
+ 19. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 
40
+ 4. Fail to appropriately disclose to end users any known dangers of your AI system
41
+ 5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.2
42
+
43
+ With respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.
44
+
45
+ Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
46
+
47
+
48
+
49
+ * Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)
50
+ * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
51
+ * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
52
+ * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.2: [email protected]
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: Tue Oct 08, 21:43:50