Hugging Face's logo

mradermacher
/
Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF

Transformers
GGUF
English
Mixture of Experts
DPO
RL-TUNED
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
52dfd49
·
verified ·
1 Parent(s): ab026e8

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -35,7 +35,10 @@ more details, including on how to concatenate multi-part files.
35
  |:-----|:-----|--------:|:------|
36
  | [GGUF](https://huggingface.co/mradermacher/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF/resolve/main/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B.Q2_K.gguf) | Q2_K | 4.9 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF/resolve/main/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B.IQ3_S.gguf) | IQ3_S | 5.7 | beats Q3_K* |
 
 
38
  | [GGUF](https://huggingface.co/mradermacher/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF/resolve/main/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B.Q4_K_S.gguf) | Q4_K_S | 7.4 | fast, recommended |
 
39
  | [GGUF](https://huggingface.co/mradermacher/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF/resolve/main/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B.Q8_0.gguf) | Q8_0 | 13.8 | fast, best quality |
40
 
41
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
35
  |:-----|:-----|--------:|:------|
36
  | [GGUF](https://huggingface.co/mradermacher/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF/resolve/main/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B.Q2_K.gguf) | Q2_K | 4.9 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF/resolve/main/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B.IQ3_S.gguf) | IQ3_S | 5.7 | beats Q3_K* |
38
+ | [GGUF](https://huggingface.co/mradermacher/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF/resolve/main/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B.IQ3_M.gguf) | IQ3_M | 5.8 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF/resolve/main/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B.Q3_K_M.gguf) | Q3_K_M | 6.3 | lower quality |
40
  | [GGUF](https://huggingface.co/mradermacher/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF/resolve/main/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B.Q4_K_S.gguf) | Q4_K_S | 7.4 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF/resolve/main/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B.Q6_K.gguf) | Q6_K | 10.7 | very good quality |
42
  | [GGUF](https://huggingface.co/mradermacher/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-GGUF/resolve/main/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B.Q8_0.gguf) | Q8_0 | 13.8 | fast, best quality |
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant