💧 Proteus-8B
Proteus-8B is a merge of the following models using Mergekit:
🧩 Configuration
tokenizer_source: union
embed_slerp: true
name: Proteus-8B
models:
- model: cognitivecomputations/dolphin-2.9-llama3-8b
parameters:
density: 0.5
weight: 0.4
- model: NousResearch/Hermes-2-Theta-Llama-3-8B
parameters:
density: 0.5
weight: 0.6
merge_method: dare_ties
base_model: NousResearch/Hermes-2-Theta-Llama-3-8B
parameters:
int8_mask: true
dtype: bfloat16
Eval Results
| Benchmark | Average | arc | gsm8k | hellaswag | mmlu | truthfulqa | winogrande |
|---|---|---|---|---|---|---|---|
| openllm | 70.67 | 63.48 | 78.77 | 82.94 | 64.71 | 56.71 | 77.43 |
Detailed Results: https://github.com/saucam/model_evals/blob/main/saucam/Proteus-8B/README.md
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "saucam/Proteus-8B"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])