Views
No views yet
1models:
2 - model: teknium/OpenHermes-2.5-Mistral-7B
3 # no parameters necessary for base model
4 - model: Yuma42/KangalKhan-RawRuby-7B
5 parameters:
6 density: 0.6
7 weight: 0.5
8 - model: Yuma42/KangalKhan-Ruby-7B-Fixed
9 parameters:
10 density: 0.6
11 weight: 0.5
12merge_method: ties
13base_model: teknium/OpenHermes-2.5-Mistral-7B
14parameters:
15 normalize: true
16dtype: bfloat161!pip install -qU transformers accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "Yuma42/KangalKhan-PressurizedRuby-7B"
8messages = [{"role": "user", "content": "What is a large language model?"}]
9
10tokenizer = AutoTokenizer.from_pretrained(model)
11prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
12pipeline = transformers.pipeline(
13 "text-generation",
14 model=model,
15 torch_dtype=torch.float16,
16 device_map="auto",
17)
18
19outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
20print(outputs[0]["generated_text"])