mradermacher commited on
Commit
6bf3f11
·
verified ·
1 Parent(s): 650036b

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -42,9 +42,14 @@ more details, including on how to concatenate multi-part files.
42
  | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
43
  | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
44
  | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
 
45
  | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
 
 
 
46
  | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
47
  | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
 
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):
 
42
  | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
43
  | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
44
  | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.IQ4_XS.gguf) | IQ4_XS | 3.7 | |
46
  | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
48
+ | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q5_K_M.gguf) | Q5_K_M | 4.9 | |
50
  | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
51
  | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/llama2-7b-dpo-full-wo-kqa_golden-ep3-GGUF/resolve/main/llama2-7b-dpo-full-wo-kqa_golden-ep3.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
53
 
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):