195 lines
7.3 KiB
Markdown
195 lines
7.3 KiB
Markdown
---
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
base_model:
|
|
- prithivMLmods/Megatron-Corpus-14B-Exp
|
|
pipeline_tag: text-generation
|
|
tags:
|
|
- open-thought
|
|
- reasoning
|
|
- math
|
|
- text-generation-inference
|
|
- elita-1
|
|
library_name: transformers
|
|
model-index:
|
|
- name: Elita-1
|
|
results:
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: IFEval (0-Shot)
|
|
type: wis-k/instruction-following-eval
|
|
split: train
|
|
args:
|
|
num_few_shot: 0
|
|
metrics:
|
|
- type: inst_level_strict_acc and prompt_level_strict_acc
|
|
value: 49.06
|
|
name: averaged accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FElita-1
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: BBH (3-Shot)
|
|
type: SaylorTwift/bbh
|
|
split: test
|
|
args:
|
|
num_few_shot: 3
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 49.93
|
|
name: normalized accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FElita-1
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: MATH Lvl 5 (4-Shot)
|
|
type: lighteval/MATH-Hard
|
|
split: test
|
|
args:
|
|
num_few_shot: 4
|
|
metrics:
|
|
- type: exact_match
|
|
value: 34.14
|
|
name: exact match
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FElita-1
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: GPQA (0-shot)
|
|
type: Idavidrein/gpqa
|
|
split: train
|
|
args:
|
|
num_few_shot: 0
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 16.78
|
|
name: acc_norm
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FElita-1
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: MuSR (0-shot)
|
|
type: TAUR-Lab/MuSR
|
|
args:
|
|
num_few_shot: 0
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 20.53
|
|
name: acc_norm
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FElita-1
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: MMLU-PRO (5-shot)
|
|
type: TIGER-Lab/MMLU-Pro
|
|
config: main
|
|
split: test
|
|
args:
|
|
num_few_shot: 5
|
|
metrics:
|
|
- type: acc
|
|
value: 48.68
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FElita-1
|
|
name: Open LLM Leaderboard
|
|
---
|
|
|
|
|
|
# **Elita-1**
|
|
|
|
Elita-1 is based on the Qwen 2.5 14B modality architecture, designed to enhance the reasoning capabilities of 14B-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 **128K tokens** and generates up to **8K 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/Elita-1"
|
|
|
|
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. **High Computational Requirements**: Due to its **14B parameters** and **128K context support**, it requires powerful GPUs or TPUs 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.
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/prithivMLmods__Elita-1-details)!
|
|
Summarized results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/contents/viewer/default/train?q=prithivMLmods%2FElita-1&sort[column]=Average%20%E2%AC%86%EF%B8%8F&sort[direction]=desc)!
|
|
|
|
| Metric |Value (%)|
|
|
|-------------------|--------:|
|
|
|**Average** | 36.52|
|
|
|IFEval (0-Shot) | 49.06|
|
|
|BBH (3-Shot) | 49.93|
|
|
|MATH Lvl 5 (4-Shot)| 34.14|
|
|
|GPQA (0-shot) | 16.78|
|
|
|MuSR (0-shot) | 20.53|
|
|
|MMLU-PRO (5-shot) | 48.68|
|
|
|