Hugging Face's logo

mradermacher
/
Reproduced-tulu2-dpo-13b-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
77e4509
·
verified ·
1 Parent(s): 949dbbf

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -18,6 +18,7 @@ quantized_by: mradermacher
18
  weighted/imatrix quants of https://huggingface.co/Junrulu/Reproduced-tulu2-dpo-13b
19
 
20
  <!-- provided-files -->
 
21
  ## Usage
22
 
23
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -46,12 +47,14 @@ more details, including on how to concatenate multi-part files.
46
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.4 | IQ3_S probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.0 | IQ3_M probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.1 | |
 
49
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 7.5 | fast on arm, low quality |
50
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 7.5 | fast on arm+i8mm, low quality |
51
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 7.5 | fast on arm+sve, low quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q4_0.gguf) | i1-Q4_0 | 7.5 | fast, low quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.5 | optimal size/speed/quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended |
 
55
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.1 | |
56
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.3 | |
57
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q6_K.gguf) | i1-Q6_K | 10.8 | practically like static Q6_K |
 
18
  weighted/imatrix quants of https://huggingface.co/Junrulu/Reproduced-tulu2-dpo-13b
19
 
20
  <!-- provided-files -->
21
+ static quants are available at https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-GGUF
22
  ## Usage
23
 
24
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
47
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.4 | IQ3_S probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.0 | IQ3_M probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.1 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.5 | prefer IQ4_XS |
51
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 7.5 | fast on arm, low quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 7.5 | fast on arm+i8mm, low quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 7.5 | fast on arm+sve, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q4_0.gguf) | i1-Q4_0 | 7.5 | fast, low quality |
55
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.5 | optimal size/speed/quality |
56
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended |
57
+ | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q4_1.gguf) | i1-Q4_1 | 8.3 | |
58
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.1 | |
59
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.3 | |
60
  | [GGUF](https://huggingface.co/mradermacher/Reproduced-tulu2-dpo-13b-i1-GGUF/resolve/main/Reproduced-tulu2-dpo-13b.i1-Q6_K.gguf) | i1-Q6_K | 10.8 | practically like static Q6_K |