prithivMLmods commited on
Commit
78700cd
·
verified ·
1 Parent(s): 2720f9c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +49 -0
README.md CHANGED
@@ -21,6 +21,8 @@ tags:
21
 
22
  ### SmolLM2-Math-IIO-1.7B-Instruct
23
 
 
 
24
  | File Name | Size | Description | Upload Status |
25
  |----------------------------------------|------------|------------------------------------------------|----------------|
26
  | `.gitattributes` | 1.52 kB | Git attributes configuration file | Uploaded |
@@ -34,4 +36,51 @@ tags:
34
  | `tokenizer_config.json` | 3.95 kB | Tokenizer configuration for loading and usage | Uploaded |
35
  | `vocab.json` | 801 kB | Vocabulary for the tokenizer | Uploaded |
36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
 
22
  ### SmolLM2-Math-IIO-1.7B-Instruct
23
 
24
+ The **SmolLM2-Math-IIO-1.7B-Instruct** model is a fine-tuned variant of the **SmolLM2-1.7B** architecture, optimized for mathematical instruction and reasoning tasks. It is particularly suited for applications that require mathematical problem-solving, logical inference, and detailed step-by-step explanations.
25
+
26
  | File Name | Size | Description | Upload Status |
27
  |----------------------------------------|------------|------------------------------------------------|----------------|
28
  | `.gitattributes` | 1.52 kB | Git attributes configuration file | Uploaded |
 
36
  | `tokenizer_config.json` | 3.95 kB | Tokenizer configuration for loading and usage | Uploaded |
37
  | `vocab.json` | 801 kB | Vocabulary for the tokenizer | Uploaded |
38
 
39
+ ### **Key Features:**
40
+
41
+ 1. **Math-Focused Capabilities:**
42
+ This model is fine-tuned to handle a wide range of mathematical queries, from simple arithmetic to complex equations and mathematical proofs.
43
+
44
+ 2. **Instruction-Tuned:**
45
+ Specifically trained to follow structured queries and deliver clear, coherent outputs based on instructions, ensuring high-quality, relevant responses to prompts.
46
+
47
+ 3. **Tokenizer & Custom Tokens:**
48
+ Includes a robust tokenizer configuration with support for mathematical notation, custom tokens, and an extended vocabulary for accurate understanding and output generation.
49
+
50
+ ---
51
+
52
+ ### **Training Details:**
53
+ - **Base Model:** [SmolLM2-1.7B](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct)
54
+ - **Dataset:** Trained on **Math-IIO-68K-Mini**, a dataset focused on mathematical instructions and logic-based queries, with a total of 68.8k examples.
55
+
56
  ---
57
+
58
+ ### **File Details:**
59
+ | **File Name** | **Size** | **Description** |
60
+ |-----------------------------------|----------------|--------------------------------------------------|
61
+ | `.gitattributes` | 1.52 kB | Git attributes configuration file. |
62
+ | `README.md` | 287 Bytes | Updated README file with model details. |
63
+ | `config.json` | 940 Bytes | Configuration file for model setup. |
64
+ | `generation_config.json` | 162 Bytes | Configuration for generation-specific settings. |
65
+ | `merges.txt` | 515 kB | Tokenizer merging rules (Byte Pair Encoding). |
66
+ | `pytorch_model.bin` | 3.42 GB | Full model weights in PyTorch format. |
67
+ | `special_tokens_map.json` | 572 Bytes | Special token mappings for the tokenizer. |
68
+ | `tokenizer.json` | 3.77 MB | Tokenizer configuration and vocabulary. |
69
+ | `tokenizer_config.json` | 3.95 kB | Tokenizer configuration for loading. |
70
+ | `vocab.json` | 801 kB | Vocabulary file for the tokenizer. |
71
+
72
+ ---
73
+
74
+ ### **Capabilities:**
75
+ - **Mathematical Problem-Solving:** Solves and explains complex mathematical problems, including algebra, calculus, and more advanced topics.
76
+ - **Instruction-Following:** Adheres to structured inputs and outputs, making it effective for generating step-by-step solutions.
77
+ - **Text Generation:** Capable of generating mathematical proofs, explanations, and educational content tailored to various user queries.
78
+
79
+ ---
80
+
81
+ ### **Usage Instructions:**
82
+ 1. **Model Setup:** Download all model files and ensure the PyTorch model weights and tokenizer configurations are included.
83
+ 2. **Inference:** Load the model in a Python environment using frameworks like PyTorch or Hugging Face's Transformers.
84
+ 3. **Customization:** Configure the model with the `config.json` and `generation_config.json` files for optimal performance during inference.
85
+
86
+ ---