mradermacher
commited on
Commit
•
ae2954d
1
Parent(s):
74ddd27
auto-patch README.md
Browse files
README.md
CHANGED
@@ -20,8 +20,8 @@ tags:
|
|
20 |
<!-- ### vocab_type: -->
|
21 |
static quants of https://huggingface.co/Markhit/CodeLlama3-8B-Python
|
22 |
|
23 |
-
|
24 |
<!-- provided-files -->
|
|
|
25 |
## Usage
|
26 |
|
27 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -34,12 +34,21 @@ more details, including on how to concatenate multi-part files.
|
|
34 |
|
35 |
| Link | Type | Size/GB | Notes |
|
36 |
|:-----|:-----|--------:|:------|
|
37 |
-
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-
|
38 |
-
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-
|
39 |
-
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-
|
40 |
-
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-
|
41 |
-
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-
|
42 |
-
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
|
44 |
|
45 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
20 |
<!-- ### vocab_type: -->
|
21 |
static quants of https://huggingface.co/Markhit/CodeLlama3-8B-Python
|
22 |
|
|
|
23 |
<!-- provided-files -->
|
24 |
+
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
|
25 |
## Usage
|
26 |
|
27 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
34 |
|
35 |
| Link | Type | Size/GB | Notes |
|
36 |
|:-----|:-----|--------:|:------|
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q2_K.gguf) | Q2_K | 3.3 | |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.IQ3_XS.gguf) | IQ3_XS | 3.6 | |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
|
40 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.IQ3_M.gguf) | IQ3_M | 3.9 | |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
|
48 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
|
49 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
|
50 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
|
51 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama3-8B-Python-GGUF/resolve/main/CodeLlama3-8B-Python.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
|
52 |
|
53 |
|
54 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|