初始化项目，由ModelHub XC社区提供模型
Model: Ashed00/SmolMath-135M Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
81
README.md
Normal file
81
README.md
Normal file
@@ -0,0 +1,81 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- Ashed00/combined_math_problems
|
||||
- openai/gsm8k
|
||||
- deepmind/aqua_rat
|
||||
base_model:
|
||||
- HuggingFaceTB/SmolLM2-135M
|
||||
---
|
||||
|
||||
# SmolMath-135M
|
||||
|
||||
SmolMath is a full finetuned version of SmolLM2-135M parameter, trained to obtain the highest math accuracy, with least drop in other text benchmarks.
|
||||
|
||||
**Important**: All training codes are present in the [Github](https://github.com/Ashu-00/SmolMath/)
|
||||
**Important**: Please refer to the [Blog](https://hackmd.io/@ashu-00/SmolMath) for methodology and Training details.
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
model_path = "Ashed00/SmolMath-135M" # Path where your fine-tuned model is saved
|
||||
from transformers import pipeline
|
||||
|
||||
pipe = pipeline("text-generation", model=model_path)
|
||||
|
||||
question = "What is 2+2?"
|
||||
|
||||
prompt = "Question: " + question + "\nAnswer:"
|
||||
|
||||
output = pipe(
|
||||
prompt,
|
||||
max_length=100,
|
||||
do_sample=False, # disable sampling for greedy decoding
|
||||
)[0]["generated_text"]
|
||||
|
||||
|
||||
```
|
||||
|
||||
## Evaluation and Performance
|
||||
|
||||
### Comparision with Base Model
|
||||
| **Metrics** | **SmolLM2-135M-8k** | **SmolMath-135M** | **Δ (Change)** |
|
||||
|-------------------|---------------------|--------------------|----------------|
|
||||
| HellaSwag | 42.1 | 41.15 | −0.95 |
|
||||
| PIQA | 68.4 | 63.55 | −4.85 |
|
||||
| CommonsenseQA | 33.9 | 33.42 | −0.48 |
|
||||
| TriviaQA | 4.1 | 0.0 | −4.10 |
|
||||
| Winogrande | 51.3 | 51.78 | +0.48 |
|
||||
| OpenBookQA | 34.6 | 30.80 | −3.80 |
|
||||
| GSM8K (0-shot)* | 0.0 | 6.9 | +6.90 |
|
||||
|
||||
|
||||
*This was evaluated using the lighteval script, which is favoured by the SmolLM2 creators in their evaluation and varies from the SmolMath prompt structure.
|
||||
|
||||
### Math Benchmarks
|
||||
|
||||
| Model | AddSub* (%) | MAWPS** (%) | GSM8K* (%) |
|
||||
|----------------------|------------|-----------|-----------|
|
||||
| apple/OpenELM-270M-Instruct | 2.14 | 2.83 | 2.05 |
|
||||
| HuggingFaceTB/SmolLM2-135M-Instruct | 1.52 |4.04 | 0.45 |
|
||||
| SmolMath-no GRPO (ours) | 9.64 | 7.47 | 6.22 |
|
||||
| SmolMath (ours) | **12.05** | **8.31** | **7.51** |
|
||||
|
||||
*Evaluated only on the test set, not included in the training
|
||||
**Evaluated on complete dataset, not included in the training
|
||||
|
||||
## Citation
|
||||
|
||||
Incase you want to use this model in your work, you can site us.
|
||||
|
||||
```
|
||||
@misc{SmolMath,
|
||||
title = {Building SmolMath: A Math Reasoning SLM Under 150M Parameters},
|
||||
url = {https://hackmd.io/@ashu-00/SmolMath},
|
||||
author = {ashu-00},
|
||||
month = {July},
|
||||
year = {2025}
|
||||
}
|
||||
|
||||
```
|
||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"_name_or_path": "SmolMath1-GRPO4-best",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 0,
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 576,
|
||||
"initializer_range": 0.041666666666666664,
|
||||
"intermediate_size": 1536,
|
||||
"is_llama_config": true,
|
||||
"max_position_embeddings": 8192,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 9,
|
||||
"num_hidden_layers": 30,
|
||||
"num_key_value_heads": 3,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_interleaved": false,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 100000,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.49.0",
|
||||
"use_cache": null,
|
||||
"vocab_size": 49152
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 0,
|
||||
"transformers_version": "4.49.0"
|
||||
}
|
||||
48901
merges.txt
Normal file
48901
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9f1cccfac24b5024184860496ae2c85874f7f3c926e558012e0e1f815251ad8e
|
||||
size 538090408
|
||||
49
special_tokens_map.json
Normal file
49
special_tokens_map.json
Normal file
@@ -0,0 +1,49 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<repo_name>",
|
||||
"<reponame>",
|
||||
"<file_sep>",
|
||||
"<filename>",
|
||||
"<gh_stars>",
|
||||
"<issue_start>",
|
||||
"<issue_comment>",
|
||||
"<issue_closed>",
|
||||
"<jupyter_start>",
|
||||
"<jupyter_text>",
|
||||
"<jupyter_code>",
|
||||
"<jupyter_output>",
|
||||
"<jupyter_script>",
|
||||
"<empty_output>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
244961
tokenizer.json
Normal file
244961
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
176
tokenizer_config.json
Normal file
176
tokenizer_config.json
Normal file
@@ -0,0 +1,176 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<repo_name>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": "<reponame>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"5": {
|
||||
"content": "<file_sep>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"6": {
|
||||
"content": "<filename>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "<gh_stars>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"8": {
|
||||
"content": "<issue_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"9": {
|
||||
"content": "<issue_comment>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"10": {
|
||||
"content": "<issue_closed>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"11": {
|
||||
"content": "<jupyter_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"12": {
|
||||
"content": "<jupyter_text>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"13": {
|
||||
"content": "<jupyter_code>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"14": {
|
||||
"content": "<jupyter_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"15": {
|
||||
"content": "<jupyter_script>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"16": {
|
||||
"content": "<empty_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<repo_name>",
|
||||
"<reponame>",
|
||||
"<file_sep>",
|
||||
"<filename>",
|
||||
"<gh_stars>",
|
||||
"<issue_start>",
|
||||
"<issue_comment>",
|
||||
"<issue_closed>",
|
||||
"<jupyter_start>",
|
||||
"<jupyter_text>",
|
||||
"<jupyter_code>",
|
||||
"<jupyter_output>",
|
||||
"<jupyter_script>",
|
||||
"<empty_output>"
|
||||
],
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"extra_special_tokens": {},
|
||||
"max_length": 8192,
|
||||
"model_max_length": 8192,
|
||||
"pad_to_multiple_of": null,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"pad_token_type_id": 0,
|
||||
"padding_side": "left",
|
||||
"stride": 0,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"truncation_side": "right",
|
||||
"truncation_strategy": "longest_first",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"vocab_size": 49152
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user