mradermacher
commited on
Commit
•
718d08d
1
Parent(s):
2037a19
auto-patch README.md
Browse files
README.md
CHANGED
@@ -36,7 +36,10 @@ more details, including on how to concatenate multi-part files.
|
|
36 |
| Link | Type | Size/GB | Notes |
|
37 |
|:-----|:-----|--------:|:------|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-70b-Python-hf-GGUF/resolve/main/OpenMath-CodeLlama-70b-Python-hf.Q2_K.gguf) | Q2_K | 25.6 | |
|
|
|
39 |
| [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-70b-Python-hf-GGUF/resolve/main/OpenMath-CodeLlama-70b-Python-hf.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
|
|
|
|
|
40 |
|
41 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
42 |
types (lower is better):
|
|
|
36 |
| Link | Type | Size/GB | Notes |
|
37 |
|:-----|:-----|--------:|:------|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-70b-Python-hf-GGUF/resolve/main/OpenMath-CodeLlama-70b-Python-hf.Q2_K.gguf) | Q2_K | 25.6 | |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-70b-Python-hf-GGUF/resolve/main/OpenMath-CodeLlama-70b-Python-hf.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/OpenMath-CodeLlama-70b-Python-hf-GGUF/resolve/main/OpenMath-CodeLlama-70b-Python-hf.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
|
41 |
+
| [PART 1](https://huggingface.co/mradermacher/OpenMath-CodeLlama-70b-Python-hf-GGUF/resolve/main/OpenMath-CodeLlama-70b-Python-hf.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/OpenMath-CodeLlama-70b-Python-hf-GGUF/resolve/main/OpenMath-CodeLlama-70b-Python-hf.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
|
42 |
+
| [PART 1](https://huggingface.co/mradermacher/OpenMath-CodeLlama-70b-Python-hf-GGUF/resolve/main/OpenMath-CodeLlama-70b-Python-hf.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/OpenMath-CodeLlama-70b-Python-hf-GGUF/resolve/main/OpenMath-CodeLlama-70b-Python-hf.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
|
43 |
|
44 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
45 |
types (lower is better):
|