mradermacher
commited on
Commit
•
907b5f2
1
Parent(s):
ff4a483
auto-patch README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ quantized_by: mradermacher
|
|
16 |
static quants of https://huggingface.co/01-ai/Yi-1.5-34B-32K
|
17 |
|
18 |
<!-- provided-files -->
|
19 |
-
weighted/imatrix quants
|
20 |
## Usage
|
21 |
|
22 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -29,8 +29,19 @@ more details, including on how to concatenate multi-part files.
|
|
29 |
|
30 |
| Link | Type | Size/GB | Notes |
|
31 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
32 |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.IQ3_S.gguf) | IQ3_S | 15.1 | beats Q3_K* |
|
|
|
|
|
|
|
|
|
33 |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.Q4_K_S.gguf) | Q4_K_S | 19.7 | fast, recommended |
|
|
|
|
|
|
|
|
|
34 |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.Q8_0.gguf) | Q8_0 | 36.6 | fast, best quality |
|
35 |
|
36 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
16 |
static quants of https://huggingface.co/01-ai/Yi-1.5-34B-32K
|
17 |
|
18 |
<!-- provided-files -->
|
19 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Yi-1.5-34B-32K-i1-GGUF
|
20 |
## Usage
|
21 |
|
22 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
29 |
|
30 |
| Link | Type | Size/GB | Notes |
|
31 |
|:-----|:-----|--------:|:------|
|
32 |
+
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.Q2_K.gguf) | Q2_K | 12.9 | |
|
33 |
+
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.IQ3_XS.gguf) | IQ3_XS | 14.3 | |
|
34 |
+
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.Q3_K_S.gguf) | Q3_K_S | 15.1 | |
|
35 |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.IQ3_S.gguf) | IQ3_S | 15.1 | beats Q3_K* |
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.IQ3_M.gguf) | IQ3_M | 15.7 | |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.Q3_K_M.gguf) | Q3_K_M | 16.8 | lower quality |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.Q3_K_L.gguf) | Q3_K_L | 18.2 | |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.IQ4_XS.gguf) | IQ4_XS | 18.7 | |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.Q4_K_S.gguf) | Q4_K_S | 19.7 | fast, recommended |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.Q4_K_M.gguf) | Q4_K_M | 20.8 | fast, recommended |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.Q5_K_S.gguf) | Q5_K_S | 23.8 | |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.Q5_K_M.gguf) | Q5_K_M | 24.4 | |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.Q6_K.gguf) | Q6_K | 28.3 | very good quality |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/Yi-1.5-34B-32K-GGUF/resolve/main/Yi-1.5-34B-32K.Q8_0.gguf) | Q8_0 | 36.6 | fast, best quality |
|
46 |
|
47 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|