Hugging Face's logo

mradermacher
/
mistral-7b-orpo-airoboros-pref-10k-GGUF

Transformers
GGUF
English
alignment-handbook
trl
orpo
Generated from Trainer
conversational
Model card Files Community
mradermacher commited on
Commit
96dea24
·
verified ·
1 Parent(s): 1aca86e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -41,6 +41,16 @@ more details, including on how to concatenate multi-part files.
41
  |:-----|:-----|--------:|:------|
42
  | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.Q2_K.gguf) | Q2_K | 2.8 | |
43
  | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
 
 
 
 
 
 
 
 
 
 
44
 
45
  Here is a handy graph by ikawrakow comparing some lower-quality quant
46
  types (lower is better):
 
41
  |:-----|:-----|--------:|:------|
42
  | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.Q2_K.gguf) | Q2_K | 2.8 | |
43
  | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
48
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
49
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/mistral-7b-orpo-airoboros-pref-10k-GGUF/resolve/main/mistral-7b-orpo-airoboros-pref-10k.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
54
 
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant
56
  types (lower is better):