mradermacher
commited on
auto-patch README.md
Browse files
README.md
CHANGED
@@ -24,7 +24,7 @@ tags:
|
|
24 |
static quants of https://huggingface.co/rhaymison/Qwen-portuguese-luana-7b
|
25 |
|
26 |
<!-- provided-files -->
|
27 |
-
weighted/imatrix quants
|
28 |
## Usage
|
29 |
|
30 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -41,9 +41,14 @@ more details, including on how to concatenate multi-part files.
|
|
41 |
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q3_K_S.gguf) | Q3_K_S | 3.7 | |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q3_K_L.gguf) | Q3_K_L | 4.3 | |
|
|
|
44 |
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
|
|
|
|
|
|
|
45 |
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
|
46 |
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q8_0.gguf) | Q8_0 | 8.3 | fast, best quality |
|
|
|
47 |
|
48 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
49 |
types (lower is better):
|
|
|
24 |
static quants of https://huggingface.co/rhaymison/Qwen-portuguese-luana-7b
|
25 |
|
26 |
<!-- provided-files -->
|
27 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-i1-GGUF
|
28 |
## Usage
|
29 |
|
30 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
41 |
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q3_K_S.gguf) | Q3_K_S | 3.7 | |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q3_K_L.gguf) | Q3_K_L | 4.3 | |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q4_K_M.gguf) | Q4_K_M | 4.9 | fast, recommended |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q5_K_S.gguf) | Q5_K_S | 5.5 | |
|
48 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q5_K_M.gguf) | Q5_K_M | 5.6 | |
|
49 |
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
|
50 |
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.Q8_0.gguf) | Q8_0 | 8.3 | fast, best quality |
|
51 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen-portuguese-luana-7b-GGUF/resolve/main/Qwen-portuguese-luana-7b.f16.gguf) | f16 | 15.5 | 16 bpw, overkill |
|
52 |
|
53 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
54 |
types (lower is better):
|