|
--- |
|
license: apache-2.0 |
|
tags: |
|
- moe |
|
- merge |
|
- mergekit |
|
- lazymergekit |
|
- mlabonne/NeuralBeagle14-7B |
|
- AdaptLLM/finance-chat |
|
- AdaptLLM/medicine-chat |
|
- AdaptLLM/law-chat |
|
datasets: |
|
- Open-Orca/OpenOrca |
|
- WizardLM/WizardLM_evol_instruct_V2_196k |
|
- EleutherAI/pile |
|
- GAIR/lima |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
🌟 Buying me coffee is a direct way to show support for this project. |
|
<a href="https://www.buymeacoffee.com/isotonic"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a> |
|
|
|
|
|
# AdaptLLM-4x7B-MoE |
|
|
|
AdaptLLM-4x7B-MoE is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): |
|
* [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B) |
|
* [AdaptLLM/finance-chat](https://huggingface.co/AdaptLLM/finance-chat) |
|
* [AdaptLLM/medicine-chat](https://huggingface.co/AdaptLLM/medicine-chat) |
|
* [AdaptLLM/law-chat](https://huggingface.co/AdaptLLM/law-chat) |
|
|
|
## 💻 Usage |
|
```python |
|
Prompt Template: |
|
|
|
<s>[INST] <<SYS>> |
|
{{ system_prompt }} |
|
<</SYS>> |
|
|
|
{{ user_message }} [/INST] |
|
``` |
|
|
|
```python |
|
!pip install -qU transformers bitsandbytes accelerate |
|
|
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
|
|
model = "Isotonic/AdaptLLM-4x7B-MoE" |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model) |
|
pipeline = transformers.pipeline( |
|
"text-generation", |
|
model=model, |
|
model_kwargs={ |
|
"torch_dtype": torch.float16, |
|
"low_cpu_mem_usage": True, |
|
"use_cache" : False, |
|
"gradient_checkpointing" : True, |
|
"device_map" : 'auto', |
|
"load_in_8bit" : True |
|
}, |
|
) |
|
|
|
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}] |
|
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
outputs = pipeline(prompt, max_new_tokens=512, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) |
|
print(outputs[0]["generated_text"]) |
|
``` |
|
|
|
## 🧩 Configuration |
|
|
|
```yaml |
|
base_model: mlabonne/NeuralBeagle14-7B |
|
experts: |
|
- source_model: mlabonne/NeuralBeagle14-7B |
|
positive_prompts: |
|
- "chat" |
|
- "assistant" |
|
- "tell me" |
|
- "explain" |
|
- "storywriting" |
|
- "write" |
|
- "scene" |
|
- "story" |
|
- "character" |
|
- "instruct" |
|
- "summarize" |
|
- "count" |
|
|
|
- source_model: AdaptLLM/finance-chat |
|
positive_prompts: |
|
- "personal finance" |
|
- "budgeting" |
|
- "investing" |
|
- "retirement planning" |
|
- "debt management" |
|
- "financial education" |
|
- "consumer protection" |
|
- "financial" |
|
- "money" |
|
- "investment" |
|
- "banking" |
|
- "stock" |
|
- "bond" |
|
- "portfolio" |
|
- "risk" |
|
- "return" |
|
|
|
- source_model: AdaptLLM/medicine-chat |
|
positive_prompts: |
|
- "diagnose" |
|
- "treat" |
|
- "disease" |
|
- "symptom" |
|
- "medication" |
|
- "anatomy" |
|
- "physiology" |
|
- "pharmacology" |
|
- "clinical trial" |
|
- "medical research" |
|
|
|
- source_model: AdaptLLM/law-chat |
|
positive_prompts: |
|
- "law" |
|
- "legal" |
|
- "attorney" |
|
- "lawyer" |
|
- "court" |
|
- "contract" |
|
- "criminal" |
|
- "evidence" |
|
- "procedure" |
|
- "contracts" |
|
- "mergers & acquisitions" |
|
- "corporate governance" |
|
- "intellectual property" |
|
- "employment law" |
|
- "international trade" |
|
- "competition law" |
|
- "antitrust" |
|
- "litigation" |
|
- "arbitration" |
|
- "mediation" |
|
``` |
