mradermacher
commited on
auto-patch README.md
Browse files
README.md
CHANGED
@@ -30,7 +30,7 @@ tags:
|
|
30 |
static quants of https://huggingface.co/ValiantLabs/CodeLlama-70B-Esper
|
31 |
|
32 |
<!-- provided-files -->
|
33 |
-
weighted/imatrix quants
|
34 |
## Usage
|
35 |
|
36 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -45,8 +45,14 @@ more details, including on how to concatenate multi-part files.
|
|
45 |
|:-----|:-----|--------:|:------|
|
46 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q2_K.gguf) | Q2_K | 25.6 | |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q3_K_S.gguf) | Q3_K_S | 30.0 | |
|
|
|
|
|
|
|
48 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
|
|
|
49 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
|
|
|
|
|
50 |
| [PART 1](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
|
51 |
|
52 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
30 |
static quants of https://huggingface.co/ValiantLabs/CodeLlama-70B-Esper
|
31 |
|
32 |
<!-- provided-files -->
|
33 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/CodeLlama-70B-Esper-i1-GGUF
|
34 |
## Usage
|
35 |
|
36 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
45 |
|:-----|:-----|--------:|:------|
|
46 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q2_K.gguf) | Q2_K | 25.6 | |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q3_K_S.gguf) | Q3_K_S | 30.0 | |
|
48 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
|
49 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
|
50 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.IQ4_XS.gguf) | IQ4_XS | 37.3 | |
|
51 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
|
52 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q4_K_M.gguf) | Q4_K_M | 41.5 | fast, recommended |
|
53 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
|
54 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q5_K_M.gguf) | Q5_K_M | 48.9 | |
|
55 |
+
| [PART 1](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
|
56 |
| [PART 1](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/CodeLlama-70B-Esper-GGUF/resolve/main/CodeLlama-70B-Esper.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
|
57 |
|
58 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|