Update README.md
Browse files
README.md
CHANGED
|
@@ -190,20 +190,6 @@ quantized_by: bartowski
|
|
| 190 |
|
| 191 |
## Exllama v2 Quantizations of Meta-Llama-3-8B-Instruct
|
| 192 |
|
| 193 |
-
If generation refuses to stop, you can edit tokenizer_config.json.
|
| 194 |
-
|
| 195 |
-
Replace line 2055:
|
| 196 |
-
|
| 197 |
-
```
|
| 198 |
-
"eos_token": "<|end_of_text|>",
|
| 199 |
-
```
|
| 200 |
-
|
| 201 |
-
with:
|
| 202 |
-
|
| 203 |
-
```
|
| 204 |
-
"eos_token": "<|eot_id|>",
|
| 205 |
-
```
|
| 206 |
-
|
| 207 |
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.19">turboderp's ExLlamaV2 v0.0.19</a> for quantization.
|
| 208 |
|
| 209 |
<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
|
|
|
|
| 190 |
|
| 191 |
## Exllama v2 Quantizations of Meta-Llama-3-8B-Instruct
|
| 192 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 193 |
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.19">turboderp's ExLlamaV2 v0.0.19</a> for quantization.
|
| 194 |
|
| 195 |
<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
|