Update README.md
Browse files
README.md
CHANGED
|
@@ -63,20 +63,6 @@ pipeline_tag: text-generation
|
|
| 63 |
|
| 64 |
## Exllama v2 Quantizations of Einstein-v6.1-Llama3-8B
|
| 65 |
|
| 66 |
-
If generation refuses to stop, you can edit tokenizer_config.json.
|
| 67 |
-
|
| 68 |
-
Replace line 2055:
|
| 69 |
-
|
| 70 |
-
```
|
| 71 |
-
"eos_token": "<|end_of_text|>",
|
| 72 |
-
```
|
| 73 |
-
|
| 74 |
-
with:
|
| 75 |
-
|
| 76 |
-
```
|
| 77 |
-
"eos_token": "<|eot_id|>",
|
| 78 |
-
```
|
| 79 |
-
|
| 80 |
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.19">turboderp's ExLlamaV2 v0.0.19</a> for quantization.
|
| 81 |
|
| 82 |
<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
|
|
|
|
| 63 |
|
| 64 |
## Exllama v2 Quantizations of Einstein-v6.1-Llama3-8B
|
| 65 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.19">turboderp's ExLlamaV2 v0.0.19</a> for quantization.
|
| 67 |
|
| 68 |
<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
|