Hugging Face's logo

RichardErkhov
/
Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf

GGUF
conversational
Model card Files
xet
Community
RichardErkhov commited on
Commit
3d8f1e6
·
verified ·
1 Parent(s): 14822c8

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +100 -0
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ VersatiLlama-Llama-3.2-3B-Instruct-Abliterated - GGUF
11
+ - Model creator: https://huggingface.co/Devarui379/
12
+ - Original model: https://huggingface.co/Devarui379/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q2_K.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q2_K.gguf) | Q2_K | 1.27GB |
18
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q3_K_S.gguf) | Q3_K_S | 1.44GB |
19
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q3_K.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q3_K.gguf) | Q3_K | 1.57GB |
20
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q3_K_M.gguf) | Q3_K_M | 1.57GB |
21
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q3_K_L.gguf) | Q3_K_L | 1.69GB |
22
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.IQ4_XS.gguf) | IQ4_XS | 1.71GB |
23
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q4_0.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q4_0.gguf) | Q4_0 | 1.79GB |
24
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.IQ4_NL.gguf) | IQ4_NL | 1.79GB |
25
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q4_K_S.gguf) | Q4_K_S | 1.8GB |
26
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q4_K.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q4_K.gguf) | Q4_K | 1.88GB |
27
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q4_K_M.gguf) | Q4_K_M | 1.88GB |
28
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q4_1.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q4_1.gguf) | Q4_1 | 1.95GB |
29
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q5_0.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q5_0.gguf) | Q5_0 | 2.11GB |
30
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q5_K_S.gguf) | Q5_K_S | 2.11GB |
31
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q5_K.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q5_K.gguf) | Q5_K | 2.16GB |
32
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q5_K_M.gguf) | Q5_K_M | 2.16GB |
33
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q5_1.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q5_1.gguf) | Q5_1 | 2.28GB |
34
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q6_K.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q6_K.gguf) | Q6_K | 2.46GB |
35
+ | [VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q8_0.gguf](https://huggingface.co/RichardErkhov/Devarui379_-_VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-gguf/blob/main/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated.Q8_0.gguf) | Q8_0 | 3.19GB |
36
+
37
+
38
+
39
+
40
+ Original model description:
41
+ ---
42
+ base_model:
43
+ - meta-llama/Llama-3.2-3B-Instruct
44
+ license: cc-by-4.0
45
+ language:
46
+ - en
47
+ pipeline_tag: text-generation
48
+ library_name: transformers
49
+ ---
50
+
51
+ # Model Card for Model ID
52
+
53
+ # VersatiLlama-Llama-3.2-3B-Instruct-Abliterated
54
+
55
+ ![image/webp](https://cdn-uploads.huggingface.co/production/uploads/66c9d7a26f2335ba288810a4/4YDg-rcEXCK0fdTS1fBzE.webp)
56
+
57
+ ### Model Description
58
+ Small but Smart
59
+
60
+ Fine-Tuned on Vast dataset of Conversations
61
+
62
+ Able to Generate Human like text with high performance within its size.
63
+
64
+ It is Very Versatile when compared for it's size and Parameters and offers capability almost as good as Llama 3.1 8B Instruct
65
+
66
+ Feel free to Check it out!!
67
+
68
+ Check the quantized model here: [Devarui379/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-Imatrix-GGUF](https://huggingface.co/Devarui379/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated-Imatrix-GGUF)
69
+
70
+ [This model was trained for 5hrs on GPU T4 15gb vram]
71
+
72
+
73
+ - **Developed by:** Meta AI
74
+ - **Fine-Tuned by:** Devarui379
75
+ - **Model type:** Transformers
76
+ - **Language(s) (NLP):** English
77
+ - **License:** cc-by-4.0
78
+
79
+ ### Model Sources [optional]
80
+
81
+ base model:meta-llama/Llama-3.2-3B-Instruct
82
+ - **Repository:** [Devarui379/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated](https://huggingface.co/Devarui379/VersatiLlama-Llama-3.2-3B-Instruct-Abliterated)
83
+ - **Demo:** Use LM Studio with the Quantized version
84
+
85
+ ## Uses
86
+
87
+ Use desired System prompt when using in LM Studio
88
+ The optimal chat template seems to be Jinja but feel free to test it out as you want!
89
+
90
+
91
+ ## Technical Specifications
92
+
93
+ ### Model Architecture and Objective
94
+
95
+ Llama 3.2
96
+
97
+ #### Hardware
98
+
99
+ NVIDIA TESLA T4 GPU 15GB VRAM
100
+