Views
No views yet
1slices:
2 - sources:
3 - model: hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode
4 parameters:
5 density: 1.0
6 weight: 0.7
7 layer_range: [0, 32]
8 - model: NousResearch/Meta-Llama-3-8B
9 layer_range: [0, 32]
10 - model: NousResearch/Meta-Llama-3-8B-Instruct
11 layer_range: [0, 32]
12merge_method: model_stock
13base_model: NousResearch/Meta-Llama-3-8B-Instruct
14parameters:
15 t:
16 - filter: self_attn
17 value: [0, 0.5, 0.3, 0.7, 1]
18 - filter: mlp
19 value: [1, 0.5, 0.7, 0.3, 0]
20 - value: 0.5
21dtype: bfloat161!pip install -qU transformers accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "Nhoodie/Meta-Llama-3-8B-Uninstruct-function-calling-json-mode-model_stock-v0.1"
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"])