Hugging Face's logo

anujjamwal
/
Qwen2.5-Math-1.5B-hcot

Text Generation
Transformers
TensorBoard
Safetensors
qwen2
Generated from Trainer
trl
sft
conversational
text-generation-inference
Model card Files
xet
 Metrics Community
anujjamwal commited on
Commit
fcf45b6
·
verified ·
1 Parent(s): df595c4

Training in progress, epoch 1

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. README.md +57 -0
  3. chat_template.jinja +7 -0
  4. config.json +62 -0
  5. generation_config.json +9 -0
  6. model.safetensors +3 -0
  7. runs/Feb23_18-51-27_3140bbd8edc3/events.out.tfevents.1771872687.3140bbd8edc3.578.0 +3 -0
  8. runs/Feb23_18-52-56_3140bbd8edc3/events.out.tfevents.1771872776.3140bbd8edc3.578.1 +3 -0
  9. runs/Feb23_20-07-44_3140bbd8edc3/events.out.tfevents.1771877264.3140bbd8edc3.578.2 +3 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +19 -0
  12. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip 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
 
 
33
  *.zip 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
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-Math-1.5B
3
+ library_name: transformers
4
+ model_name: Qwen2.5-Math-1.5B-hcot
5
+ tags:
6
+ - generated_from_trainer
7
+ - trl
8
+ - sft
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for Qwen2.5-Math-1.5B-hcot
13
+
14
+ This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B).
15
+ It has been trained using [TRL](https://github.com/huggingface/trl).
16
+
17
+ ## Quick start
18
+
19
+ ```python
20
+ from transformers import pipeline
21
+
22
+ 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?"
23
+ generator = pipeline("text-generation", model="anujjamwal/Qwen2.5-Math-1.5B-hcot", device="cuda")
24
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
+ print(output["generated_text"])
26
+ ```
27
+
28
+ ## Training procedure
29
+
30
+
31
+
32
+
33
+ This model was trained with SFT.
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 0.28.0
38
+ - Transformers: 5.0.0
39
+ - Pytorch: 2.10.0+cu128
40
+ - Datasets: 4.0.0
41
+ - Tokenizers: 0.22.2
42
+
43
+ ## Citations
44
+
45
+
46
+
47
+ Cite TRL as:
48
+
49
+ ```bibtex
50
+ @software{vonwerra2020trl,
51
+ title = {{TRL: Transformers Reinforcement Learning}},
52
+ author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
53
+ license = {Apache-2.0},
54
+ url = {https://github.com/huggingface/trl},
55
+ year = {2020}
56
+ }
57
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if message['role'] == 'system' %}<|im_start|>system
2
+ {{ message['content'] }}<|im_end|>
3
+ {% elif message['role'] == 'user' %}<|im_start|>user
4
+ {{ message['content'] }}<|im_end|>
5
+ {% elif message['role'] == 'assistant' %}<|im_start|>assistant
6
+ {% generation %}{{ message['content'] }}{% endgeneration %}<|im_end|>
7
+ {% endif %}{% endfor %}
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": null,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
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
+ ],
43
+ "max_position_embeddings": 4096,
44
+ "max_window_layers": 21,
45
+ "model_type": "qwen2",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 2,
49
+ "pad_token_id": 151643,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_parameters": {
52
+ "rope_theta": 10000,
53
+ "rope_type": "default"
54
+ },
55
+ "sliding_window": null,
56
+ "tie_word_embeddings": true,
57
+ "transformers_version": "5.0.0",
58
+ "use_cache": false,
59
+ "use_mrope": false,
60
+ "use_sliding_window": false,
61
+ "vocab_size": 151668
62
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": false,
3
+ "eos_token_id": [
4
+ 151643
5
+ ],
6
+ "max_new_tokens": 2048,
7
+ "pad_token_id": 151643,
8
+ "transformers_version": "5.0.0"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a631570fc65201db27b0741d19c3fdcdb71cc4678063e28d610ee15e31feb26
3
+ size 4268442032
runs/Feb23_18-51-27_3140bbd8edc3/events.out.tfevents.1771872687.3140bbd8edc3.578.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d2923d482c192c646f24e0b2f708a8ed7ff9265d8baf98c642fad8016564eeb
3
+ size 19423
runs/Feb23_18-52-56_3140bbd8edc3/events.out.tfevents.1771872776.3140bbd8edc3.578.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36abce149815672fb0630a759750a089e5faba33f7f07e6d3d68ff31bb143f84
3
+ size 442179
runs/Feb23_20-07-44_3140bbd8edc3/events.out.tfevents.1771877264.3140bbd8edc3.578.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:949663832859c11f55603b555a2c895174bf061ce172d6a89dabb74aeadb389a
3
+ size 21700
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be3e81ad4a729cf43b0a2eb03504fea95988d21bce9eb8b320a2baae5e7d438
3
+ size 11422450
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "[THOUGHT]",
10
+ "[SOLUTION]",
11
+ "[RETURN]"
12
+ ],
13
+ "is_local": false,
14
+ "model_max_length": 131072,
15
+ "pad_token": "<|endoftext|>",
16
+ "split_special_tokens": false,
17
+ "tokenizer_class": "Qwen2Tokenizer",
18
+ "unk_token": null
19
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:104a0bd5e2bcb84faa81c3f1194aa5371a9e71d80bfdd0a4995d4cd83b35a1f0
3
+ size 5713