prithivMLmods commited on
Commit
8b21d19
1 Parent(s): a777b97

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +53 -0
README.md CHANGED
@@ -19,6 +19,8 @@ tags:
19
  ---
20
  ### **QwQ-4B-Instruct-Model-Files**
21
 
 
 
22
  | **File Name** | **Size** | **Description** | **Upload Status** |
23
  |----------------------------------|-----------------|---------------------------------------------------|-------------------|
24
  | `.gitattributes` | 1.57 kB | Tracks files stored with Git LFS. | Uploaded |
@@ -35,4 +37,55 @@ tags:
35
  | `tokenizer_config.json` | 7.73 kB | Settings for the tokenizer integration. | Uploaded |
36
  | `vocab.json` | 2.78 MB | Vocabulary file containing token-to-id mappings. | Uploaded |
37
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  ---
20
  ### **QwQ-4B-Instruct-Model-Files**
21
 
22
+ The **QwQ-4B-Instruct** is a lightweight and efficient fine-tuned language model for instruction-following tasks and reasoning. It is based on a quantized version of the **Qwen2.5-7B** model, optimized for inference speed and reduced memory consumption, while retaining robust capabilities for complex tasks.
23
+
24
  | **File Name** | **Size** | **Description** | **Upload Status** |
25
  |----------------------------------|-----------------|---------------------------------------------------|-------------------|
26
  | `.gitattributes` | 1.57 kB | Tracks files stored with Git LFS. | Uploaded |
 
37
  | `tokenizer_config.json` | 7.73 kB | Settings for the tokenizer integration. | Uploaded |
38
  | `vocab.json` | 2.78 MB | Vocabulary file containing token-to-id mappings. | Uploaded |
39
 
40
+ ### **Key Features:**
41
+
42
+ 1. **Model Size:**
43
+ - **4.46B parameters.**
44
+
45
+ 2. **Precision Support:**
46
+ - Available in multiple tensor types:
47
+ - **FP16**
48
+ - **F32**
49
+ - **U8 (Quantized)**
50
+
51
+ 3. **Model Sharding:**
52
+ - The model weights are stored in two parts for efficient download:
53
+ - `model-00001-of-00002.safetensors` (4.46 GB)
54
+ - `model-00002-of-00002.safetensors` (1.09 GB)
55
+ - Indexed with `model.safetensors.index.json`.
56
+
57
+ 4. **Tokenizer:**
58
+ - Uses Byte-Pair Encoding (BPE).
59
+ - Includes:
60
+ - `vocab.json` (2.78 MB)
61
+ - `merges.txt` (1.82 MB)
62
+ - `tokenizer.json` (11.4 MB, pre-trained configuration).
63
+ - Special tokens mapped in `special_tokens_map.json` (e.g., `<pad>`, `<eos>`).
64
+
65
+ 5. **Configuration Files:**
66
+ - `config.json`: Defines the architecture, hyperparameters, and settings.
67
+ - `generation_config.json`: Specifies text generation behavior (e.g., max length, temperature).
68
+
69
  ---
70
+
71
+ ### **Training Dataset:**
72
+ - **Dataset Name:** [amphora/QwQ-LongCoT-130K](https://huggingface.co/amphora/QwQ-LongCoT-130K)
73
+ - **Size:** 133k examples.
74
+ - **Focus:** Chain-of-Thought reasoning for detailed and logical outputs.
75
+
76
+ ---
77
+
78
+ ### **Use Cases:**
79
+ 1. **Instruction-Following:**
80
+ - Excels in handling concise and multi-step instructions.
81
+
82
+ 2. **Reasoning:**
83
+ - Well-suited for tasks requiring logical deductions and detailed explanations.
84
+
85
+ 3. **Text Generation:**
86
+ - Generates coherent and contextually aware responses across various domains.
87
+
88
+ 4. **Resource-Constrained Applications:**
89
+ - Optimized for scenarios requiring lower computational resources due to its smaller model size and quantization.
90
+
91
+ ---