Views
No views yet
1base_model: cognitivecomputations/dolphin-2.8-mistral-7b-v02
2gate_mode: hidden
3dtype: bfloat16
4experts_per_token: 2
5experts:
6 - source_model: Open-Orca/Mistral-7B-OpenOrca
7 positive_prompts:
8 - "What are some fun activities to do in Seattle?"
9 - "What are some fun historical facts about New York City?"
10 negative_prompts:
11 - "Write a Python script to scrape data from a website."
12 - "Explain the key differences between Bayesian and frequentist statistics."
13
14 - source_model: NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
15 positive_prompts:
16 - "Write me a fictional story about dragons and wizards?"
17 - "From now on take on the role of Dwayne Johnson"
18 negative_prompts:
19 - "When is the next solar eclipse."
20 - "What year did World War II end?"
21
22 - source_model: S-miguel/The-Trinity-Coder-7B
23 positive_prompts:
24 - "Can you review my JavaScript code and suggest ways to optimize it for better performance?"
25 - "I'm getting an 'undefined variable' error in my Python script. Here's the code: [code snippet]"
26 negative_prompts:
27 - "What are some effective strategies for managing stress and anxiety?"
28 - "Compare and contrast the themes in 'The Great Gatsby' and 'The Catcher in the Rye'."
29
30 - source_model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
31 positive_prompts:
32 - "What's a square root of 1337?"
33 - "Find the midpoint of the line segment with the given end points (-5,7) and (-2,1)"
34 negative_prompts:
35 - "What are some effective strategies for managing stress and anxiety?"
36 - "Compare and contrast the themes in 'The Great Gatsby' and 'The Catcher in the Rye'."1!pip install -qU transformers bitsandbytes accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "jambroz/sixtyoneeighty-7b-MOE"
8
9tokenizer = AutoTokenizer.from_pretrained(model)
10pipeline = transformers.pipeline(
11 "text-generation",
12 model=model,
13 model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
14)
15
16messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
17prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
18outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
19print(outputs[0]["generated_text"])