Hugging Face's logo

RichardErkhov
/
princeton-nlp_-_Llama-3-Base-8B-SFT-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
RichardErkhov commited on
Commit
ae72078
•
1 Parent(s): 372c316

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +46 -0
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ Llama-3-Base-8B-SFT - GGUF
11
+ - Model creator: https://huggingface.co/princeton-nlp/
12
+ - Original model: https://huggingface.co/princeton-nlp/Llama-3-Base-8B-SFT/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [Llama-3-Base-8B-SFT.Q2_K.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q2_K.gguf) | Q2_K | 2.96GB |
18
+ | [Llama-3-Base-8B-SFT.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
19
+ | [Llama-3-Base-8B-SFT.IQ3_S.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.IQ3_S.gguf) | IQ3_S | 1.61GB |
20
+ | [Llama-3-Base-8B-SFT.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q3_K_S.gguf) | Q3_K_S | 0.77GB |
21
+ | [Llama-3-Base-8B-SFT.IQ3_M.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.IQ3_M.gguf) | IQ3_M | 3.52GB |
22
+ | [Llama-3-Base-8B-SFT.Q3_K.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q3_K.gguf) | Q3_K | 3.74GB |
23
+ | [Llama-3-Base-8B-SFT.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
24
+ | [Llama-3-Base-8B-SFT.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
25
+ | [Llama-3-Base-8B-SFT.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
26
+ | [Llama-3-Base-8B-SFT.Q4_0.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q4_0.gguf) | Q4_0 | 4.34GB |
27
+ | [Llama-3-Base-8B-SFT.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
28
+ | [Llama-3-Base-8B-SFT.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
29
+ | [Llama-3-Base-8B-SFT.Q4_K.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q4_K.gguf) | Q4_K | 4.58GB |
30
+ | [Llama-3-Base-8B-SFT.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
31
+ | [Llama-3-Base-8B-SFT.Q4_1.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q4_1.gguf) | Q4_1 | 4.78GB |
32
+ | [Llama-3-Base-8B-SFT.Q5_0.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q5_0.gguf) | Q5_0 | 5.21GB |
33
+ | [Llama-3-Base-8B-SFT.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
34
+ | [Llama-3-Base-8B-SFT.Q5_K.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q5_K.gguf) | Q5_K | 5.34GB |
35
+ | [Llama-3-Base-8B-SFT.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
36
+ | [Llama-3-Base-8B-SFT.Q5_1.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q5_1.gguf) | Q5_1 | 5.65GB |
37
+ | [Llama-3-Base-8B-SFT.Q6_K.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q6_K.gguf) | Q6_K | 6.14GB |
38
+ | [Llama-3-Base-8B-SFT.Q8_0.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Base-8B-SFT-gguf/blob/main/Llama-3-Base-8B-SFT.Q8_0.gguf) | Q8_0 | 7.95GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ This is a model released from the preprint: *[SimPO: Simple Preference Optimization with a Reference-Free Reward](https://arxiv.org/abs/2405.14734)* Please refer to our [repository](https://github.com/princeton-nlp/SimPO) for more details.
45
+
46
+