Hugging Face's logo

mradermacher
/
shisa-7b-v1-sharegpt-GGUF

Transformers
GGUF
English
axolotl
Generated from Trainer
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
bc7288b
·
verified ·
1 Parent(s): 80b70e1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -33,7 +33,17 @@ more details, including on how to concatenate multi-part files.
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
35
  | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q2_K.gguf) | Q2_K | 3.2 | |
 
 
 
 
 
36
  | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q4_K_S.gguf) | Q4_K_S | 4.7 | fast, recommended |
 
 
 
 
 
37
  | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.f16.gguf) | f16 | 16.0 | 16 bpw, overkill |
38
 
39
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
33
  | Link | Type | Size/GB | Notes |
34
  |:-----|:-----|--------:|:------|
35
  | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q2_K.gguf) | Q2_K | 3.2 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q3_K_S.gguf) | Q3_K_S | 3.7 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
38
+ | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.IQ4_XS.gguf) | IQ4_XS | 4.5 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.7 | fast on arm, low quality |
41
  | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q4_K_S.gguf) | Q4_K_S | 4.7 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q5_K_S.gguf) | Q5_K_S | 5.6 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q6_K.gguf) | Q6_K | 6.6 | very good quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
47
  | [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.f16.gguf) | f16 | 16.0 | 16 bpw, overkill |
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant