Hugging Face's logo

tobil
/
qmd-query-expansion-1.7B

Safetensors
GGUF
qwen3
conversational
Model card Files
xet
 Community
tobil commited on
Commit
8256ad8
·
verified ·
1 Parent(s): 3f25db2

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. .gitattributes +1 -0
  2. README.md +47 -44
  3. config.json +63 -0
  4. generation_config.json +13 -0
  5. model.safetensors +3 -0
  6. qmd-query-expansion-1.7B.gguf +3 -0
  7. tokenizer.json +2 -2
  8. tokenizer_config.json +3 -228
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ qmd-query-expansion-1.7B.gguf filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,59 +1,62 @@
1
  ---
 
2
  base_model: Qwen/Qwen3-1.7B
3
- library_name: transformers
4
- model_name: qmd-query-expansion-1.7B
5
  tags:
6
- - generated_from_trainer
7
- - hf_jobs
8
- - trl
9
- - sft
10
- licence: license
 
 
 
11
  ---
12
 
13
- # Model Card for qmd-query-expansion-1.7B
14
 
15
- This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B).
16
- It has been trained using [TRL](https://github.com/huggingface/trl).
17
 
18
- ## Quick start
19
 
20
- ```python
21
- from transformers import pipeline
22
-
23
- question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
24
- generator = pipeline("text-generation", model="tobil/qmd-query-expansion-1.7B", device="cuda")
25
- output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
26
- print(output["generated_text"])
27
  ```
28
 
29
- ## Training procedure
30
-
31
-
32
-
33
-
34
- This model was trained with SFT.
35
-
36
- ### Framework versions
 
 
37
 
38
- - TRL: 0.27.0
39
- - Transformers: 4.57.6
40
- - Pytorch: 2.10.0
41
- - Datasets: 4.5.0
42
- - Tokenizers: 0.22.2
43
 
44
- ## Citations
 
 
 
 
45
 
 
 
 
 
 
 
 
 
 
 
46
 
 
47
 
48
- Cite TRL as:
49
-
50
- ```bibtex
51
- @misc{vonwerra2022trl,
52
- title = {{TRL: Transformer Reinforcement Learning}},
53
- author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
54
- year = 2020,
55
- journal = {GitHub repository},
56
- publisher = {GitHub},
57
- howpublished = {\url{https://github.com/huggingface/trl}}
58
- }
59
- ```
 
1
  ---
2
+ license: apache-2.0
3
  base_model: Qwen/Qwen3-1.7B
 
 
4
  tags:
5
+ - query-expansion
6
+ - search
7
+ - retrieval
8
+ - rag
9
+ - hybrid-search
10
+ language:
11
+ - en
12
+ pipeline_tag: text-generation
13
  ---
14
 
15
+ # QMD Query Expansion 1.7B
16
 
17
+ A Qwen3-1.7B model finetuned for query expansion in hybrid search systems (RAG).
 
18
 
19
+ ## Usage
20
 
21
+ Input format:
22
+ ```
23
+ Expand this search query:
24
+ <your query here>
 
 
 
25
  ```
26
 
27
+ Output format (7 lines):
28
+ ```
29
+ hyde: <hypothetical document snippet 50-200 chars>
30
+ lex: <keyword phrase for BM25>
31
+ lex: <keyword phrase>
32
+ lex: <keyword phrase>
33
+ vec: <semantic sentence for vector search>
34
+ vec: <semantic sentence>
35
+ vec: <semantic sentence>
36
+ ```
37
 
38
+ ## Example
 
 
 
 
39
 
40
+ **Input:**
41
+ ```
42
+ Expand this search query:
43
+ postgresql jsonb indexing
44
+ ```
45
 
46
+ **Output:**
47
+ ```
48
+ hyde: PostgreSQL JSONB supports GIN indexes for fast key lookups and containment queries.
49
+ lex: postgresql jsonb gin index
50
+ lex: postgres json indexing
51
+ lex: jsonb index optimization
52
+ vec: How do I create efficient indexes on JSONB columns in PostgreSQL?
53
+ vec: Best practices for indexing JSON data in PostgreSQL databases.
54
+ vec: Performance comparison of GIN vs BTREE indexes for JSONB fields.
55
+ ```
56
 
57
+ ## Training
58
 
59
+ - Base: Qwen/Qwen3-1.7B
60
+ - Method: SFT with LoRA, merged
61
+ - Data: GEPA-distilled from GPT-4o-mini teacher
62
+ - Scores: 80-96% on evaluation queries
 
 
 
 
 
 
 
 
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 6144,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention"
44
+ ],
45
+ "max_position_embeddings": 40960,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen3",
48
+ "num_attention_heads": 16,
49
+ "num_hidden_layers": 28,
50
+ "num_key_value_heads": 8,
51
+ "pad_token_id": null,
52
+ "rms_norm_eps": 1e-06,
53
+ "rope_parameters": {
54
+ "rope_theta": 1000000,
55
+ "rope_type": "default"
56
+ },
57
+ "sliding_window": null,
58
+ "tie_word_embeddings": true,
59
+ "transformers_version": "5.0.0",
60
+ "use_cache": true,
61
+ "use_sliding_window": false,
62
+ "vocab_size": 151936
63
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.0.0"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e520db129fa6880692fe68a22d475b222f95725691c9298e9d3246e9274a3a55
3
+ size 4063515640
qmd-query-expansion-1.7B.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e48154d4706d36727b150bdb5c08c027369d62762560fe57d228879e97096408
3
+ size 4069679392
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
- size 11422654
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer_config.json CHANGED
@@ -1,239 +1,14 @@
1
  {
2
- "add_bos_token": false,
3
  "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "151643": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "151644": {
14
- "content": "<|im_start|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "151645": {
22
- "content": "<|im_end|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "151648": {
46
- "content": "<|box_start|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "151649": {
54
- "content": "<|box_end|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "151657": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "151658": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- },
181
- "151665": {
182
- "content": "<tool_response>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": false
188
- },
189
- "151666": {
190
- "content": "</tool_response>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": false
196
- },
197
- "151667": {
198
- "content": "<think>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": false
204
- },
205
- "151668": {
206
- "content": "</think>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": false
212
- }
213
- },
214
- "additional_special_tokens": [
215
- "<|im_start|>",
216
- "<|im_end|>",
217
- "<|object_ref_start|>",
218
- "<|object_ref_end|>",
219
- "<|box_start|>",
220
- "<|box_end|>",
221
- "<|quad_start|>",
222
- "<|quad_end|>",
223
- "<|vision_start|>",
224
- "<|vision_end|>",
225
- "<|vision_pad|>",
226
- "<|image_pad|>",
227
- "<|video_pad|>"
228
- ],
229
  "bos_token": null,
230
  "clean_up_tokenization_spaces": false,
231
  "eos_token": "<|im_end|>",
232
  "errors": "replace",
233
- "extra_special_tokens": {},
234
  "model_max_length": 131072,
235
  "pad_token": "<|endoftext|>",
236
  "split_special_tokens": false,
237
  "tokenizer_class": "Qwen2Tokenizer",
238
  "unk_token": null
239
- }
 
1
  {
 
2
  "add_prefix_space": false,
3
+ "backend": "tokenizers",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "bos_token": null,
5
  "clean_up_tokenization_spaces": false,
6
  "eos_token": "<|im_end|>",
7
  "errors": "replace",
8
+ "is_local": false,
9
  "model_max_length": 131072,
10
  "pad_token": "<|endoftext|>",
11
  "split_special_tokens": false,
12
  "tokenizer_class": "Qwen2Tokenizer",
13
  "unk_token": null
14
+ }