s-emanuilov commited on
Commit
c40538c
·
verified ·
1 Parent(s): 829fef4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +64 -2
README.md CHANGED
@@ -1,7 +1,69 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
3
  datasets:
4
  - s-emanuilov/query-expansion
5
  base_model:
6
- - Qwen/Qwen2.5-7B-Instruct
7
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ tags:
4
+ - llama.cpp
5
+ - gguf
6
+ - query-expansion
7
  datasets:
8
  - s-emanuilov/query-expansion
9
  base_model:
10
+ - Qwen/Qwen2.5-7B-GGUF
11
+ ---
12
+ # Query Expansion GGUF - based on Qwen2.5-7B
13
+
14
+ GGUF quantized version of Qwen2.5-7B for query expansion task.
15
+ Part of a collection of query expansion models available in different architectures and sizes.
16
+
17
+ ## Overview
18
+
19
+ **Task:** Search query expansion
20
+ **Base model:** [Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B)
21
+ **Training data:** [Query Expansion Dataset](https://huggingface.co/datasets/s-emanuilov/query-expansion)
22
+
23
+ <img src="static/query-expansion-model.jpg" alt="Query Expansion Model" width="600px" />
24
+
25
+ ## Quantized Versions
26
+
27
+ Model available in multiple quantization formats:
28
+ - F16 (Original size)
29
+ - Q8_0 (~8-bit quantization)
30
+ - Q5_K_M (~5-bit quantization)
31
+ - Q4_K_M (~4-bit quantization)
32
+ - Q3_K_M (~3-bit quantization)
33
+
34
+ ## Related Models
35
+
36
+ ### LoRA Adaptors
37
+ - [Qwen2.5-3B](https://huggingface.co/s-emanuilov/query-expansion-Qwen2.5-3B)
38
+ - [Qwen2.5-7B](https://huggingface.co/s-emanuilov/query-expansion-Qwen2.5-7B)
39
+ - [Llama-3.2-3B](https://huggingface.co/s-emanuilov/query-expansion-Llama-3.2-3B)
40
+
41
+ ### GGUF Variants
42
+ - [Qwen2.5-7B-GGUF](https://huggingface.co/s-emanuilov/query-expansion-Qwen2.5-7B-GGUF)
43
+ - [Llama-3.2-3B-GGUF](https://huggingface.co/s-emanuilov/query-expansion-Llama-3.2-3B-GGUF)
44
+
45
+ ## Details
46
+ This model is designed for enhancing search and retrieval systems by generating semantically relevant query expansions.
47
+
48
+ It could be useful for:
49
+ - Advanced RAG systems
50
+ - Search enhancement
51
+ - Query preprocessing
52
+ - Low-latency query expansion
53
+
54
+ ## Example
55
+
56
+ **Input:** "apple stock"
57
+ **Expansions:**
58
+ - "current apple share value"
59
+ - "latest updates on apple's market position"
60
+ - "how is apple performing in the current market?"
61
+ - "what is the latest information on apple's financial standing?"
62
+
63
+ ## Citation
64
+
65
+ If you find my work helpful, feel free to give me a citation.
66
+
67
+ ```
68
+
69
+ ```