Hugging Face's logo

mradermacher
/
Llama-3.1-8B-ContinuedTraining2-FFT-GGUF

Transformers
GGUF
English
llama
llm
fine-tuning
fill-in-the-middle
instruction-following
Model card Files
xet
Community
mradermacher commited on
Commit
dd18a84
·
verified ·
1 Parent(s): ae471be

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -44,9 +44,14 @@ more details, including on how to concatenate multi-part files.
44
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
 
47
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
 
 
 
48
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
49
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
 
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):
 
44
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
49
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
50
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
52
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
54
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ContinuedTraining2-FFT-GGUF/resolve/main/Llama-3.1-8B-ContinuedTraining2-FFT.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
55
 
56
  Here is a handy graph by ikawrakow comparing some lower-quality quant
57
  types (lower is better):