Commit
•
ddfc772
1
Parent(s):
fe752fe
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,10 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
language:
|
| 4 |
- en
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
This is an experimental coding-focused merge of the latest of two of my favorite projects which have trained and fine-tuned the Qwen2 model on open source data:
|
|
@@ -10,7 +14,7 @@ Replete-AI's Replete LLM Qwen2-7B (https://huggingface.co/Replete-AI/Replete-LLM
|
|
| 10 |
|
| 11 |
The GGUF is quantized to q8_0 for output and embedding tensors, q5_k_m for others.
|
| 12 |
|
| 13 |
-
If there is interest, I will publish the huggingface repo; otherwise, the dare_ties mergekit YAML that produced it is already included.
|
| 14 |
|
| 15 |
I asked it to describe itself, given its own mergekit YAML and points from the web pages for its two ancestor models:
|
| 16 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
+
pipeline_tag: text-classification
|
| 6 |
+
tags:
|
| 7 |
+
- code
|
| 8 |
+
- not-for-all-audiences
|
| 9 |
---
|
| 10 |
|
| 11 |
This is an experimental coding-focused merge of the latest of two of my favorite projects which have trained and fine-tuned the Qwen2 model on open source data:
|
|
|
|
| 14 |
|
| 15 |
The GGUF is quantized to q8_0 for output and embedding tensors, q5_k_m for others.
|
| 16 |
|
| 17 |
+
The experimental nature and Replete LLM Qwen2-7B lack of censorship means that you take all responsibility for how you use this model. If there is interest, I will publish the huggingface repo; otherwise, the dare_ties mergekit YAML that produced it is already included.
|
| 18 |
|
| 19 |
I asked it to describe itself, given its own mergekit YAML and points from the web pages for its two ancestor models:
|
| 20 |
|