metadata
license: apache-2.0
🧩 Configuration
base_model: /home/Ubuntu/Desktop/mergekit/models/Mistral-7B-Instruct-v0.2
gate_mode: hidden
dtype: bfloat16
experts:
- source_model: /home/Ubuntu/Desktop/mergekit/models/Mistral-7B-Instruct-v0.2
positive_prompts:
- "instructions"
- "concise"
- "straightforward"
- "helpful"
- "assistant"
negative_prompts:
- "vague"
- "inaccurate"
- "verbose"
- "complicated"
- "speculative"
- source_model: /home/Ubuntu/Desktop/mergekit/models/NeuralOmniWestBeaglake-7B
positive_prompts:
- "storytelling"
- "role play"
- "imagine"
- "artistic"
- "narrative"
- source_model: /home/Ubuntu/Desktop/mergekit/models/Kunoichi-DPO-v2-7B
positive_prompts:
- "reason"
- "think step by step"
- "logic"
- "knowledge"
negative_prompts:
- "artistic"
- "speculative"
- "playful"
- source_model: /home/Ubuntu/Desktop/mergekit/models/Starling-LM-7B-alpha
positive_prompts:
- "code"
- "python"
- "javascript"
- "react"
- "clear"
- "programming"
negative_prompts:
- "error"
- "art"
- "role play"
💻 Usage
!pip install -qU transformers bitsandbytes accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mayacinka/West-Ramen-7Bx4"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": 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=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])