mradermacher
commited on
Commit
•
b9b2b63
1
Parent(s):
ad39d96
auto-patch README.md
Browse files
README.md
CHANGED
@@ -179,7 +179,6 @@ tags:
|
|
179 |
<!-- ### vocab_type: -->
|
180 |
static quants of https://huggingface.co/NurtureAI/Meta-Llama-3-70B-Instruct-64k
|
181 |
|
182 |
-
|
183 |
<!-- provided-files -->
|
184 |
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.
|
185 |
## Usage
|
@@ -196,6 +195,7 @@ more details, including on how to concatenate multi-part files.
|
|
196 |
|:-----|:-----|--------:|:------|
|
197 |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
|
198 |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
|
|
|
199 |
|
200 |
|
201 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
179 |
<!-- ### vocab_type: -->
|
180 |
static quants of https://huggingface.co/NurtureAI/Meta-Llama-3-70B-Instruct-64k
|
181 |
|
|
|
182 |
<!-- provided-files -->
|
183 |
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.
|
184 |
## Usage
|
|
|
195 |
|:-----|:-----|--------:|:------|
|
196 |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
|
197 |
| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
|
198 |
+
| [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-64k-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-64k.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
|
199 |
|
200 |
|
201 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|