Views
No views yet

1slices:
2- sources:
3 - layer_range: [0, 20]
4 model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
5- sources:
6 - layer_range: [10, 30]
7 model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
8- sources:
9 - layer_range: [20, 40]
10 model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
11- sources:
12 - layer_range: [30, 50]
13 model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
14- sources:
15 - layer_range: [40, 60]
16 model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
17- sources:
18 - layer_range: [50, 70]
19 model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
20- sources:
21 - layer_range: [60, 80]
22 model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
23merge_method: passthrough
24dtype: float16<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
1!pip install -qU transformers accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "DarqueDante/LLama-3-Dolphin-2.9.1-120b"
8messages = [{"role": "user", "content": "Who is Andrej Karpathy?"}]
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"])