mukel commited on
Commit
10dad00
1 Parent(s): 52fd30d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -4
README.md CHANGED
@@ -1,11 +1,34 @@
1
  ---
2
- base_model: Qwen/Qwen2.5-3B-Instruct
 
3
  language:
4
  - en
5
- license: other
6
- license_name: qwen-research
7
- license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE
8
  pipeline_tag: text-generation
 
9
  tags:
10
  - chat
 
11
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: apache-2.0
3
+ license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct-GGUF/blob/main/LICENSE
4
  language:
5
  - en
6
+ base_model:
7
+ - Qwen/Qwen2.5-3B-Instruct
 
8
  pipeline_tag: text-generation
9
+ quantized_by: mukel
10
  tags:
11
  - chat
12
+ - qwen
13
  ---
14
+
15
+ # GGUF models for qwen2.java
16
+ Pure .gguf Q4_0 and Q8_0 quantizations of Qwen 2.5 models, ready to consume by `qwen2.java`.
17
+
18
+ In the wild, Q8_0 quantizations are fine, but Q4_0 quantizations are rarely pure e.g. the token embeddings are quantized with Q6_K, instead of Q4_0.
19
+ A pure Q4_0 quantization can be generated from a high precision (F32, F16, BFLOAT16) .gguf source with the llama-quantize utility from llama.cpp as follows:
20
+
21
+ ```
22
+ ./llama-quantize --pure ./Qwen-2.5-7B-Instruct-BF16.gguf ./Qwen-2.5-7B-Instruct-Q4_0.gguf Q4_0
23
+ ```
24
+
25
+ ## Introduction
26
+
27
+ Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:
28
+
29
+ - Significantly **more knowledge** and has greatly improved capabilities in **coding** and **mathematics**, thanks to our specialized expert models in these domains.
30
+ - Significant improvements in **instruction following**, **generating long texts** (over 8K tokens), **understanding structured data** (e.g, tables), and **generating structured outputs** especially JSON. **More resilient to the diversity of system prompts**, enhancing role-play implementation and condition-setting for chatbots.
31
+ - **Long-context Support** up to 128K tokens and can generate up to 8K tokens.
32
+ - **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
33
+
34
+ For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/).