Update README.md
Browse files
README.md
CHANGED
@@ -2,8 +2,104 @@
|
|
2 |
library_name: transformers.js
|
3 |
base_model:
|
4 |
- prithivMLmods/Lang-Exster-0.5B-Instruct
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
---
|
6 |
|
7 |
# Lang-Exster-0.5B-Instruct (ONNX)
|
8 |
|
9 |
This is an ONNX version of [prithivMLmods/Lang-Exster-0.5B-Instruct](https://huggingface.co/prithivMLmods/Lang-Exster-0.5B-Instruct). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
library_name: transformers.js
|
3 |
base_model:
|
4 |
- prithivMLmods/Lang-Exster-0.5B-Instruct
|
5 |
+
license: apache-2.0
|
6 |
+
language:
|
7 |
+
- en
|
8 |
+
pipeline_tag: text-generation
|
9 |
+
tags:
|
10 |
+
- text-generation-inference
|
11 |
+
- code
|
12 |
---
|
13 |
|
14 |
# Lang-Exster-0.5B-Instruct (ONNX)
|
15 |
|
16 |
This is an ONNX version of [prithivMLmods/Lang-Exster-0.5B-Instruct](https://huggingface.co/prithivMLmods/Lang-Exster-0.5B-Instruct). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
|
17 |
+
|
18 |
+

|
19 |
+
|
20 |
+
# **Lang-Exster-0.5B-Instruct**
|
21 |
+
|
22 |
+
> **Lang-Exster-0.5B-Instruct** is a **general-purpose instruction-following LLM** fine-tuned from **Qwen2.5-0.5B**. This model is optimized for **lightweight deployments** and **instructional clarity**, capable of performing a wide range of natural language and programming-related tasks with efficiency and interpretability.
|
23 |
+
|
24 |
+
## **Key Features**
|
25 |
+
|
26 |
+
1. **Instruction Following & Explanation**
|
27 |
+
Trained to **understand, follow, and respond** to natural language instructions with clear, logical, and relevant output. Suitable for Q&A, step-by-step reasoning, and guided code generation.
|
28 |
+
|
29 |
+
2. **Lightweight General-Purpose Model**
|
30 |
+
Fine-tuned from **Qwen2.5-0.5B**, making it **highly efficient for edge devices**, **local tools**, and **low-resource applications** without sacrificing utility.
|
31 |
+
|
32 |
+
3. **Multi-Domain Task Handling**
|
33 |
+
Can perform across **coding**, **writing**, **summarization**, **chat**, **translation**, and **educational queries**, thanks to its broad general-purpose instruction tuning.
|
34 |
+
|
35 |
+
4. **Compact and Efficient**
|
36 |
+
At just **0.5B parameters**, Lang-Exster is optimized for **fast inference**, **low memory usage**, and seamless integration into developer tools and workflows.
|
37 |
+
|
38 |
+
5. **Code Assistance (Lite)**
|
39 |
+
Capable of **basic code generation**, **syntax checking**, and **conceptual explanations**, especially useful for beginners and instructional applications.
|
40 |
+
|
41 |
+
## **Quickstart with Transformers**
|
42 |
+
|
43 |
+
```python
|
44 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
45 |
+
|
46 |
+
model_name = "prithivMLmods/Lang-Exster-0.5B-Instruct"
|
47 |
+
|
48 |
+
model = AutoModelForCausalLM.from_pretrained(
|
49 |
+
model_name,
|
50 |
+
torch_dtype="auto",
|
51 |
+
device_map="auto"
|
52 |
+
)
|
53 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
54 |
+
|
55 |
+
prompt = "Write a Python function that checks if a number is prime, and explain how it works."
|
56 |
+
|
57 |
+
messages = [
|
58 |
+
{"role": "system", "content": "You are an instructional assistant. Follow user instructions clearly and explain your reasoning."},
|
59 |
+
{"role": "user", "content": prompt}
|
60 |
+
]
|
61 |
+
text = tokenizer.apply_chat_template(
|
62 |
+
messages,
|
63 |
+
tokenize=False,
|
64 |
+
add_generation_prompt=True
|
65 |
+
)
|
66 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
67 |
+
|
68 |
+
generated_ids = model.generate(
|
69 |
+
**model_inputs,
|
70 |
+
max_new_tokens=512
|
71 |
+
)
|
72 |
+
generated_ids = [
|
73 |
+
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
74 |
+
]
|
75 |
+
|
76 |
+
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
77 |
+
```
|
78 |
+
|
79 |
+
## **Intended Use**
|
80 |
+
|
81 |
+
- **General-Purpose Assistant**:
|
82 |
+
Performs everyday tasks such as Q&A, summarization, light coding, language generation, and translation.
|
83 |
+
|
84 |
+
- **Educational Support**:
|
85 |
+
Aids learners in understanding topics through **guided explanations**, **basic coding help**, and **concept breakdowns**.
|
86 |
+
|
87 |
+
- **Lightweight Developer Integration**:
|
88 |
+
Ideal for command-line assistants, browser plugins, and desktop utilities with limited compute resources.
|
89 |
+
|
90 |
+
- **Instruction Clarity Demonstrator**:
|
91 |
+
Acts as a fine baseline for developing **instruction-tuned** capabilities in constrained environments.
|
92 |
+
|
93 |
+
## **Limitations**
|
94 |
+
|
95 |
+
1. **Scale Limitations**
|
96 |
+
Being a 0.5B model, it has limited memory and may not handle deep context or long documents effectively.
|
97 |
+
|
98 |
+
2. **Reasoning Depth**
|
99 |
+
Provides **surface-level reasoning** and may struggle with highly technical, abstract, or creative prompts.
|
100 |
+
|
101 |
+
3. **Basic Code Generation**
|
102 |
+
Supports basic scripting and logic but may miss edge cases or advanced patterns in complex code.
|
103 |
+
|
104 |
+
4. **Prompt Design Sensitivity**
|
105 |
+
Performs best with **clear**, **concise**, and **well-structured** instructions.
|