Update README.md
Browse files
README.md
CHANGED
@@ -1,30 +1,30 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
language:
|
4 |
-
- en
|
5 |
-
base_model:
|
6 |
-
- Qwen/Qwen2.5-Coder-0.5B
|
7 |
-
pipeline_tag: text-generation
|
8 |
-
library_name: transformers
|
9 |
-
tags:
|
10 |
-
- code
|
11 |
-
- qwen
|
12 |
-
- qwen2.5
|
13 |
-
- qwen-coder
|
14 |
-
- codeqwen
|
15 |
-
- deepseek
|
16 |
-
---
|
17 |
-
|
18 |
-
# DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B
|
19 |
-
|
20 |
-
**Updated**
|
21 |
-
|
22 |
-
This model is trained on CODE outputs of <a href="https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B">deepseek-ai/DeepSeek-R1-Distill-Qwen-32B</a> and is meant to be used only as draft model for speculative decoding.
|
23 |
-
|
24 |
-
It's specifically intended for users of 3090/4090, allowing you to run the DeepSeek-R1-Distill-Qwen-32B-Q4_K_M GGUF version with 16k context and speeding up generation without sacrificing more context length or model quality.
|
25 |
-
|
26 |
-
# Data info
|
27 |
-
|
28 |
-
The data consists of code tasks collected from various datasets. It has been trained for 2 epochs on 2.5k unique examples, for a total of 7.6 million tokens per epoch.
|
29 |
-
|
30 |
Since data generation was done using spare GPU time, I may publish a further trained version later.
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
base_model:
|
6 |
+
- Qwen/Qwen2.5-Coder-0.5B
|
7 |
+
pipeline_tag: text-generation
|
8 |
+
library_name: transformers
|
9 |
+
tags:
|
10 |
+
- code
|
11 |
+
- qwen
|
12 |
+
- qwen2.5
|
13 |
+
- qwen-coder
|
14 |
+
- codeqwen
|
15 |
+
- deepseek
|
16 |
+
---
|
17 |
+
|
18 |
+
# DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B
|
19 |
+
|
20 |
+
**Updated to v1**
|
21 |
+
|
22 |
+
This model is trained on CODE outputs of <a href="https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B">deepseek-ai/DeepSeek-R1-Distill-Qwen-32B</a> and is meant to be used only as draft model for speculative decoding.
|
23 |
+
|
24 |
+
It's specifically intended for users of 3090/4090, allowing you to run the DeepSeek-R1-Distill-Qwen-32B-Q4_K_M GGUF version with 16k context and speeding up generation without sacrificing more context length or model quality.
|
25 |
+
|
26 |
+
# Data info
|
27 |
+
|
28 |
+
The data consists of code tasks collected from various datasets. It has been trained for 2 epochs on 2.5k unique examples, for a total of 7.6 million tokens per epoch.
|
29 |
+
|
30 |
Since data generation was done using spare GPU time, I may publish a further trained version later.
|