mradermacher
commited on
Commit
•
b108be9
1
Parent(s):
b669657
auto-patch README.md
Browse files
README.md
CHANGED
@@ -18,7 +18,7 @@ tags:
|
|
18 |
static quants of https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf
|
19 |
|
20 |
<!-- provided-files -->
|
21 |
-
weighted/imatrix quants
|
22 |
## Usage
|
23 |
|
24 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -32,8 +32,18 @@ more details, including on how to concatenate multi-part files.
|
|
32 |
| Link | Type | Size/GB | Notes |
|
33 |
|:-----|:-----|--------:|:------|
|
34 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.Q2_K.gguf) | Q2_K | 2.6 | |
|
|
|
35 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* |
|
|
|
|
|
|
|
|
|
|
|
36 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
|
|
|
|
|
|
|
|
|
37 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
|
38 |
|
39 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
18 |
static quants of https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf
|
19 |
|
20 |
<!-- provided-files -->
|
21 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-i1-GGUF
|
22 |
## Usage
|
23 |
|
24 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
32 |
| Link | Type | Size/GB | Notes |
|
33 |
|:-----|:-----|--------:|:------|
|
34 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.Q2_K.gguf) | Q2_K | 2.6 | |
|
35 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.IQ3_XS.gguf) | IQ3_XS | 2.9 | |
|
36 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.IQ3_M.gguf) | IQ3_M | 3.2 | |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
|
40 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.IQ4_XS.gguf) | IQ4_XS | 3.7 | |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.Q5_K_M.gguf) | Q5_K_M | 4.9 | |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/CodeLlama-7b-Instruct-hf-GGUF/resolve/main/CodeLlama-7b-Instruct-hf.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
|
48 |
|
49 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|