mradermacher
commited on
Commit
•
26eb782
1
Parent(s):
f7b6515
auto-patch README.md
Browse files
README.md
CHANGED
@@ -23,7 +23,7 @@ quantized_by: mradermacher
|
|
23 |
static quants of https://huggingface.co/ChocoLlama/ChocoLlama-2-7B-instruct
|
24 |
|
25 |
<!-- provided-files -->
|
26 |
-
weighted/imatrix quants
|
27 |
## Usage
|
28 |
|
29 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -40,9 +40,12 @@ more details, including on how to concatenate multi-part files.
|
|
40 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
|
|
|
|
|
43 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
|
|
|
46 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
|
48 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
|
|
|
23 |
static quants of https://huggingface.co/ChocoLlama/ChocoLlama-2-7B-instruct
|
24 |
|
25 |
<!-- provided-files -->
|
26 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-i1-GGUF
|
27 |
## Usage
|
28 |
|
29 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
40 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q3_K_S.gguf) | Q3_K_S | 3.0 | |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q3_K_L.gguf) | Q3_K_L | 3.7 | |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.IQ4_XS.gguf) | IQ4_XS | 3.7 | |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended |
|
46 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q5_K_S.gguf) | Q5_K_S | 4.8 | |
|
48 |
+
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q5_K_M.gguf) | Q5_K_M | 4.9 | |
|
49 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q6_K.gguf) | Q6_K | 5.6 | very good quality |
|
50 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality |
|
51 |
| [GGUF](https://huggingface.co/mradermacher/ChocoLlama-2-7B-instruct-GGUF/resolve/main/ChocoLlama-2-7B-instruct.f16.gguf) | f16 | 13.6 | 16 bpw, overkill |
|