78 lines
3.8 KiB
Markdown
78 lines
3.8 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
base_model:
|
||
|
|
- prithivMLmods/QwQ-LCoT2-7B-Instruct
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- sqweeks
|
||
|
|
- reasoner
|
||
|
|
- qwen
|
||
|
|
- 7b
|
||
|
|
---
|
||
|
|
# **Sqweeks-7B-Instruct**
|
||
|
|
|
||
|
|
Sqweeks-7B-Instruct is based on the Qwen 2.5 7B modality architecture, designed to enhance the reasoning capabilities of 7B-parameter models. It has been fine-tuned on a synthetic dataset based on open-thoughts & general corpus reasoning entries, further optimizing its chain-of-thought (CoT) reasoning and logical problem-solving abilities. The model demonstrates significant improvements in context understanding, structured data processing, and long-context comprehension, making it ideal for complex reasoning tasks, instruction-following, and text generation.
|
||
|
|
|
||
|
|
### **Key Improvements**
|
||
|
|
1. **Enhanced Knowledge and Expertise**: Improved mathematical reasoning, coding proficiency, and structured data processing.
|
||
|
|
2. **Fine-Tuned Instruction Following**: Optimized for precise responses, structured outputs (e.g., JSON), and generating long texts (8K+ tokens).
|
||
|
|
3. **Greater Adaptability**: Better role-playing capabilities and resilience to diverse system prompts.
|
||
|
|
4. **Long-Context Support**: Handles up to **64K tokens** and generates up to **4K tokens** per output.
|
||
|
|
5. **Multilingual Proficiency**: Supports over **29 languages**, including Chinese, English, French, Spanish, Portuguese, German, and more.
|
||
|
|
|
||
|
|
### **Quickstart with Transformers**
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
|
|
|
||
|
|
model_name = "prithivMLmods/Sqweeks-7B-Instruct"
|
||
|
|
|
||
|
|
model = AutoModelForCausalLM.from_pretrained(
|
||
|
|
model_name,
|
||
|
|
torch_dtype="auto",
|
||
|
|
device_map="auto",
|
||
|
|
trust_remote_code=True
|
||
|
|
)
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||
|
|
|
||
|
|
prompt = "Give me a short introduction to large language models."
|
||
|
|
messages = [
|
||
|
|
{"role": "system", "content": "You are an advanced AI assistant with expert-level reasoning and knowledge."},
|
||
|
|
{"role": "user", "content": prompt}
|
||
|
|
]
|
||
|
|
text = tokenizer.apply_chat_template(
|
||
|
|
messages,
|
||
|
|
tokenize=False,
|
||
|
|
add_generation_prompt=True
|
||
|
|
)
|
||
|
|
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||
|
|
|
||
|
|
generated_ids = model.generate(
|
||
|
|
**model_inputs,
|
||
|
|
max_new_tokens=512
|
||
|
|
)
|
||
|
|
generated_ids = [
|
||
|
|
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
||
|
|
]
|
||
|
|
|
||
|
|
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
||
|
|
print(response)
|
||
|
|
```
|
||
|
|
|
||
|
|
### **Intended Use**
|
||
|
|
- **Advanced Reasoning & Context Understanding**: Designed for logical deduction, multi-step problem-solving, and complex knowledge-based tasks.
|
||
|
|
- **Mathematical & Scientific Problem-Solving**: Enhanced capabilities for calculations, theorem proving, and scientific queries.
|
||
|
|
- **Code Generation & Debugging**: Generates and optimizes code across multiple programming languages.
|
||
|
|
- **Structured Data Analysis**: Processes tables, JSON, and structured outputs, making it ideal for data-centric tasks.
|
||
|
|
- **Multilingual Applications**: High proficiency in over 29 languages, enabling global-scale applications.
|
||
|
|
- **Extended Content Generation**: Supports detailed document writing, research reports, and instructional guides.
|
||
|
|
|
||
|
|
### **Limitations**
|
||
|
|
1. **Computational Requirements**: Despite being a **7B-parameter** model, it still requires a capable GPU for efficient inference.
|
||
|
|
2. **Language-Specific Variability**: Performance may vary across supported languages, especially for low-resource languages.
|
||
|
|
3. **Potential Error Accumulation**: Long-text generation can sometimes introduce inconsistencies over extended outputs.
|
||
|
|
4. **Limited Real-World Awareness**: Knowledge is restricted to training data and may not reflect recent world events.
|
||
|
|
5. **Prompt Sensitivity**: Outputs can depend on the specificity and clarity of the input prompt.
|