317 lines
12 KiB
Markdown
317 lines
12 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
license: apache-2.0
|
|
library_name: transformers
|
|
tags:
|
|
- merge
|
|
- mergekit
|
|
- lazymergekit
|
|
- bfloat16
|
|
- roleplay
|
|
- creative
|
|
- instruct
|
|
- anvita
|
|
- qwen
|
|
- nerd
|
|
- homer
|
|
- Qandora
|
|
base_model:
|
|
- bunnycore/Qandora-2.5-7B-Creative
|
|
- allknowingroger/HomerSlerp1-7B
|
|
- sethuiyer/Qwen2.5-7B-Anvita
|
|
- fblgit/cybertron-v4-qw7B-MGS
|
|
- jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0
|
|
- newsbang/Homer-v0.5-Qwen2.5-7B
|
|
pipeline_tag: text-generation
|
|
model-index:
|
|
- name: Qwen2.5-7B-HomerAnvita-NerdMix
|
|
results:
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: IFEval (0-Shot)
|
|
type: HuggingFaceH4/ifeval
|
|
args:
|
|
num_few_shot: 0
|
|
metrics:
|
|
- type: inst_level_strict_acc and prompt_level_strict_acc
|
|
value: 77.08
|
|
name: strict accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: BBH (3-Shot)
|
|
type: BBH
|
|
args:
|
|
num_few_shot: 3
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 36.58
|
|
name: normalized accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: MATH Lvl 5 (4-Shot)
|
|
type: hendrycks/competition_math
|
|
args:
|
|
num_few_shot: 4
|
|
metrics:
|
|
- type: exact_match
|
|
value: 29.53
|
|
name: exact match
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: GPQA (0-shot)
|
|
type: Idavidrein/gpqa
|
|
args:
|
|
num_few_shot: 0
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 9.28
|
|
name: acc_norm
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
|
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: 14.41
|
|
name: acc_norm
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
|
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: 38.13
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
|
name: Open LLM Leaderboard
|
|
---
|
|
|
|
# ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
|
|
|
|
**ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix** is an advanced language model meticulously crafted by merging five pre-trained models using the powerful [mergekit](https://github.com/cg123/mergekit) framework. This fusion leverages the **Model Stock** merge method to combine the creative prowess of **Qandora**, the instructive capabilities of **Qwen-Instruct-Fusion**, the sophisticated blending of **HomerSlerp1**, the mathematical precision of **Cybertron-MGS**, and the uncensored expertise of **Qwen-Nerd**. The resulting model excels in creative text generation, contextual understanding, technical reasoning, and dynamic conversational interactions.
|
|
|
|
## 🚀 Merged Models
|
|
|
|
This model merge incorporates the following:
|
|
|
|
- [**bunnycore/Qandora-2.5-7B-Creative**](https://huggingface.co/bunnycore/Qandora-2.5-7B-Creative): Specializes in creative text generation, enhancing the model's ability to produce imaginative and diverse content.
|
|
|
|
- [**allknowingroger/HomerSlerp1-7B**](https://huggingface.co/allknowingroger/HomerSlerp1-7B): Utilizes spherical linear interpolation (SLERP) to blend model weights smoothly, ensuring a harmonious integration of different model attributes.
|
|
|
|
- [**sethuiyer/Qwen2.5-7B-Anvita**](https://huggingface.co/sethuiyer/Qwen2.5-7B-Anvita): Focuses on instruction-following capabilities, improving the model's performance in understanding and executing user commands.
|
|
|
|
- [**fblgit/cybertron-v4-qw7B-MGS**](https://huggingface.co/fblgit/cybertron-v4-qw7B-MGS): Enhances mathematical reasoning and precision, enabling the model to handle complex computational tasks effectively.
|
|
|
|
- [**jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0**](https://huggingface.co/jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0): Provides uncensored expertise and robust technical knowledge, making the model suitable for specialized technical support and information retrieval.
|
|
|
|
- [**newsbang/Homer-v0.5-Qwen2.5-7B**](https://huggingface.co/newsbang/Homer-v0.5-Qwen2.5-7B): Acts as the foundational conversational model, providing robust language comprehension and generation capabilities.
|
|
|
|
## 🧩 Merge Configuration
|
|
|
|
The configuration below outlines how the models are merged using the **Model Stock** method. This approach ensures a balanced and effective integration of the unique strengths from each source model.
|
|
|
|
```yaml
|
|
# Merge configuration for ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix using Model Stock
|
|
|
|
models:
|
|
- model: bunnycore/Qandora-2.5-7B-Creative
|
|
- model: allknowingroger/HomerSlerp1-7B
|
|
- model: sethuiyer/Qwen2.5-7B-Anvita
|
|
- model: fblgit/cybertron-v4-qw7B-MGS
|
|
- model: jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0
|
|
merge_method: model_stock
|
|
base_model: newsbang/Homer-v0.5-Qwen2.5-7B
|
|
normalize: false
|
|
int8_mask: true
|
|
dtype: bfloat16
|
|
```
|
|
|
|
### Key Parameters
|
|
|
|
- **Merge Method (`merge_method`):** Utilizes the **Model Stock** method, as described in [Model Stock](https://arxiv.org/abs/2403.19522), to effectively combine multiple models by leveraging their strengths.
|
|
|
|
- **Models (`models`):** Specifies the list of models to be merged:
|
|
- **bunnycore/Qandora-2.5-7B-Creative:** Enhances creative text generation.
|
|
- **allknowingroger/HomerSlerp1-7B:** Facilitates smooth blending of model weights using SLERP.
|
|
- **sethuiyer/Qwen2.5-7B-Anvita:** Improves instruction-following capabilities.
|
|
- **fblgit/cybertron-v4-qw7B-MGS:** Enhances mathematical reasoning and precision.
|
|
- **jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0:** Provides uncensored technical expertise.
|
|
|
|
- **Base Model (`base_model`):** Defines the foundational model for the merge, which is **newsbang/Homer-v0.5-Qwen2.5-7B** in this case.
|
|
|
|
- **Normalization (`normalize`):** Set to `false` to retain the original scaling of the model weights during the merge.
|
|
|
|
- **INT8 Mask (`int8_mask`):** Enabled (`true`) to apply INT8 quantization masking, optimizing the model for efficient inference without significant loss in precision.
|
|
|
|
- **Data Type (`dtype`):** Uses `bfloat16` to maintain computational efficiency while ensuring high precision.
|
|
|
|
## 🏆 Performance Highlights
|
|
|
|
- **Creative Text Generation:** Enhanced ability to produce imaginative and diverse content suitable for creative writing, storytelling, and content creation.
|
|
|
|
- **Instruction Following:** Improved performance in understanding and executing user instructions, making the model more responsive and accurate in task execution.
|
|
|
|
- **Mathematical Reasoning:** Enhanced capability to handle complex computational tasks with high precision, suitable for technical and analytical applications.
|
|
|
|
- **Uncensored Technical Expertise:** Provides robust technical knowledge without content restrictions, making it ideal for specialized technical support and information retrieval.
|
|
|
|
|
|
- **Optimized Inference:** INT8 masking and `bfloat16` data type contribute to efficient computation, enabling faster response times without compromising quality.
|
|
|
|
## 🎯 Use Case & Applications
|
|
|
|
**ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix** is designed to excel in environments that demand a combination of creative generation, precise instruction following, mathematical reasoning, and technical expertise. Ideal applications include:
|
|
|
|
- **Creative Writing Assistance:** Aiding authors and content creators in generating imaginative narratives, dialogues, and descriptive text.
|
|
|
|
- **Interactive Storytelling and Role-Playing:** Enhancing dynamic and engaging interactions in role-playing games and interactive storytelling platforms.
|
|
|
|
- **Educational Tools and Tutoring Systems:** Providing detailed explanations, answering questions, and assisting in educational content creation with contextual understanding.
|
|
|
|
- **Technical Support and Customer Service:** Offering accurate and contextually relevant responses in technical support scenarios, improving user satisfaction.
|
|
|
|
- **Content Generation for Marketing:** Creating compelling and diverse marketing copy, social media posts, and promotional material with creative flair.
|
|
|
|
- **Mathematical Problem Solving:** Assisting in solving complex mathematical problems and providing step-by-step explanations for educational purposes.
|
|
|
|
- **Technical Documentation and Analysis:** Generating detailed technical documents, reports, and analyses with high precision and clarity.
|
|
|
|
## 📝 Usage
|
|
|
|
To utilize **ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix**, follow the steps below:
|
|
|
|
### Installation
|
|
|
|
First, install the necessary libraries:
|
|
|
|
```bash
|
|
pip install -qU transformers accelerate
|
|
```
|
|
|
|
### Example Code
|
|
|
|
Below is an example of how to load and use the model for text generation:
|
|
|
|
```python
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
|
|
import torch
|
|
|
|
# Define the model name
|
|
model_name = "ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix"
|
|
|
|
# Load the tokenizer
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
|
|
# Load the model
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
model_name,
|
|
torch_dtype=torch.bfloat16,
|
|
device_map="auto"
|
|
)
|
|
|
|
# Initialize the pipeline
|
|
text_generator = pipeline(
|
|
"text-generation",
|
|
model=model,
|
|
tokenizer=tokenizer,
|
|
torch_dtype=torch.bfloat16,
|
|
device_map="auto"
|
|
)
|
|
|
|
# Define the input prompt
|
|
prompt = "Explain the significance of artificial intelligence in modern healthcare."
|
|
|
|
# Generate the output
|
|
outputs = text_generator(
|
|
prompt,
|
|
max_new_tokens=150,
|
|
do_sample=True,
|
|
temperature=0.7,
|
|
top_k=50,
|
|
top_p=0.95
|
|
)
|
|
|
|
# Print the generated text
|
|
print(outputs[0]["generated_text"])
|
|
```
|
|
|
|
### Notes
|
|
|
|
- **Fine-Tuning:** This merged model may require fine-tuning to optimize performance for specific applications or domains.
|
|
|
|
- **Resource Requirements:** Ensure that your environment has sufficient computational resources, especially GPU-enabled hardware, to handle the model efficiently during inference.
|
|
|
|
- **Customization:** Users can adjust parameters such as `temperature`, `top_k`, and `top_p` to control the creativity and diversity of the generated text.
|
|
|
|
|
|
## 📜 License
|
|
|
|
This model is open-sourced under the **Apache-2.0 License**.
|
|
|
|
## 💡 Tags
|
|
|
|
- `merge`
|
|
- `mergekit`
|
|
- `model_stock`
|
|
- `Qwen`
|
|
- `Homer`
|
|
- `Anvita`
|
|
- `Nerd`
|
|
- `ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix`
|
|
- `bunnycore/Qandora-2.5-7B-Creative`
|
|
- `allknowingroger/HomerSlerp1-7B`
|
|
- `sethuiyer/Qwen2.5-7B-Anvita`
|
|
- `fblgit/cybertron-v4-qw7B-MGS`
|
|
- `jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.0`
|
|
- `newsbang/Homer-v0.5-Qwen2.5-7B`
|
|
|
|
---
|
|
# [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/details_ZeroXClem__Qwen2.5-7B-HomerAnvita-NerdMix)
|
|
|
|
| Metric |Value|
|
|
|-------------------|----:|
|
|
|Avg. |34.17|
|
|
|IFEval (0-Shot) |77.08|
|
|
|BBH (3-Shot) |36.58|
|
|
|MATH Lvl 5 (4-Shot)|29.53|
|
|
|GPQA (0-shot) | 9.28|
|
|
|MuSR (0-shot) |14.41|
|
|
|MMLU-PRO (5-shot) |38.13|
|
|
|