Views
No views yet
1models:
2 - model: CorticalStack/neurotic-crown-clown-7b-ties
3 - model: liminerity/M7-7b
4 parameters:
5 density: 0.52
6 weight: 0.4
7 - model: Kukedlc/NeuralSirKrishna-7b
8 parameters:
9 density: 0.52
10 weight: 0.3
11 - model: Kukedlc/Neural4gsm8k
12 parameters:
13 density: 0.52
14 weight: 0.2
15merge_method: dare_ties
16base_model: CorticalStack/neurotic-crown-clown-7b-ties
17parameters:
18 int8_mask: true
19dtype: bfloat161!pip install -qU transformers accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "Kukedlc/NeuralKrishnaMath-7B-slerp"
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"])