Hugging Face's logo

mradermacher
/
Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF

Transformers
GGUF
English
medical
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
dc72847
•
1 Parent(s): 651c8d1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -0
README.md CHANGED
@@ -33,14 +33,26 @@ more details, including on how to concatenate multi-part files.
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
 
36
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ1_M.gguf) | i1-IQ1_M | 3.2 | mostly desperate |
 
 
 
37
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ2_M.gguf) | i1-IQ2_M | 4.6 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q2_K.gguf) | i1-Q2_K | 5.0 | IQ3_XXS probably better |
39
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality |
 
 
 
40
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ3_M.gguf) | i1-IQ3_M | 6.1 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.4 | IQ3_S probably better |
 
 
 
42
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.5 | optimal size/speed/quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended |
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q6_K.gguf) | i1-Q6_K | 10.8 | practically like static Q6_K |
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
36
+ | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ1_S.gguf) | i1-IQ1_S | 3.0 | for the desperate |
37
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ1_M.gguf) | i1-IQ1_M | 3.2 | mostly desperate |
38
+ | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.6 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ2_S.gguf) | i1-IQ2_S | 4.3 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ2_M.gguf) | i1-IQ2_M | 4.6 | |
42
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q2_K.gguf) | i1-Q2_K | 5.0 | IQ3_XXS probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.5 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ3_S.gguf) | i1-IQ3_S | 5.8 | beats Q3_K* |
46
+ | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.8 | IQ3_XS probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ3_M.gguf) | i1-IQ3_M | 6.1 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.4 | IQ3_S probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.0 | IQ3_M probably better |
50
+ | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.1 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q4_0.gguf) | i1-Q4_0 | 7.5 | fast, low quality |
52
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.5 | optimal size/speed/quality |
53
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended |
54
+ | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.1 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.3 | |
56
  | [GGUF](https://huggingface.co/mradermacher/Asclepius-Llama2-13B-Pretraining-Only-i1-GGUF/resolve/main/Asclepius-Llama2-13B-Pretraining-Only.i1-Q6_K.gguf) | i1-Q6_K | 10.8 | practically like static Q6_K |
57
 
58
  Here is a handy graph by ikawrakow comparing some lower-quality quant