Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- NewEden/Roleplay-Logs-Sharegpt-Ngram-cleaned
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
base_model:
|
| 8 |
+
- toasterai/Qwen2.5-7B-SambaV1DialogTesting-001
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
tags:
|
| 11 |
+
- unsloth
|
| 12 |
+
- dialogue
|
| 13 |
+
---
|
| 14 |
+
ChatML as always. Full-precision this time. Quants will come later.
|
| 15 |
+
|
| 16 |
+
An experiment to make causal models more conversational. Many of them can already chat, but suffer from problems like occasional dullness, incoherence and verbatim repetition. This model DOES NOT follow assistant-style instructions and IS NOT INTENDED TO.
|