Commit
•
c862122
1
Parent(s):
ab47f15
auto-patch README.md
Browse files
README.md
CHANGED
@@ -4,7 +4,7 @@ language:
|
|
4 |
- en
|
5 |
library_name: transformers
|
6 |
license: mit
|
7 |
-
no_imatrix:
|
8 |
quantized_by: mradermacher
|
9 |
---
|
10 |
## About
|
@@ -32,6 +32,15 @@ more details, including on how to concatenate multi-part files.
|
|
32 |
| Link | Type | Size/GB | Notes |
|
33 |
|:-----|:-----|--------:|:------|
|
34 |
| [GGUF](https://huggingface.co/mradermacher/webby_whale_33b_v1-i1-GGUF/resolve/main/webby_whale_33b_v1.i1-Q2_K.gguf) | i1-Q2_K | 12.5 | IQ3_XXS probably better |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
|
36 |
|
37 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
4 |
- en
|
5 |
library_name: transformers
|
6 |
license: mit
|
7 |
+
no_imatrix: 'GGML_ASSERT: /root/cvs/llama.cpp/ggml-quants.c:11239: grid_index >= 0'
|
8 |
quantized_by: mradermacher
|
9 |
---
|
10 |
## About
|
|
|
32 |
| Link | Type | Size/GB | Notes |
|
33 |
|:-----|:-----|--------:|:------|
|
34 |
| [GGUF](https://huggingface.co/mradermacher/webby_whale_33b_v1-i1-GGUF/resolve/main/webby_whale_33b_v1.i1-Q2_K.gguf) | i1-Q2_K | 12.5 | IQ3_XXS probably better |
|
35 |
+
| [GGUF](https://huggingface.co/mradermacher/webby_whale_33b_v1-i1-GGUF/resolve/main/webby_whale_33b_v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/webby_whale_33b_v1-i1-GGUF/resolve/main/webby_whale_33b_v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.2 | IQ3_S probably better |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/webby_whale_33b_v1-i1-GGUF/resolve/main/webby_whale_33b_v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.7 | IQ3_M probably better |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/webby_whale_33b_v1-i1-GGUF/resolve/main/webby_whale_33b_v1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 19.0 | slightly worse than Q4_K_S |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/webby_whale_33b_v1-i1-GGUF/resolve/main/webby_whale_33b_v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 19.0 | optimal size/speed/quality |
|
40 |
+
| [GGUF](https://huggingface.co/mradermacher/webby_whale_33b_v1-i1-GGUF/resolve/main/webby_whale_33b_v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/webby_whale_33b_v1-i1-GGUF/resolve/main/webby_whale_33b_v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 23.1 | |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/webby_whale_33b_v1-i1-GGUF/resolve/main/webby_whale_33b_v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.6 | |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/webby_whale_33b_v1-i1-GGUF/resolve/main/webby_whale_33b_v1.i1-Q6_K.gguf) | i1-Q6_K | 27.5 | practically like static Q6_K |
|
44 |
|
45 |
|
46 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|