Hugging Face's logo

mradermacher
/
I-Code-NousLlama7B-slerp-GGUF

Transformers
GGUF
English
Merge
mergekit
lazymergekit
NousResearch/CodeLlama-7b-hf
NousResearch/Llama-2-7b-chat-hf
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
9c09166
·
verified ·
1 Parent(s): 9c8881a

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -39,7 +39,14 @@ more details, including on how to concatenate multi-part files.
39
  | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
40
  | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
41
  | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
 
42
  | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
 
 
 
 
 
 
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant
45
  types (lower is better):
 
39
  | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
40
  | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
41
  | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.IQ4_XS.gguf) | IQ4_XS | 3.7 | |
43
  | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
44
+ | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
45
+ | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.Q5_K_M.gguf) | Q5_K_M | 4.9 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/I-Code-NousLlama7B-slerp-GGUF/resolve/main/I-Code-NousLlama7B-slerp.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):