KingNish-Llama3-8b-v0.2-2
KingNish-Llama3-8b-v0.2-2 is a merge of the following models using LazyMergekit:
- VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
- mlabonne/ChimeraLlama-3-8B-v3
- MaziyarPanahi/Llama-3-8B-Instruct-v0.4
𧩠Configuration
models:
- model: KingNish/KingNish-Llama3-8b
# No parameters necessary for base model
- model: VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
parameters:
density: 0.7
weight: 0.5
- model: mlabonne/ChimeraLlama-3-8B-v3
parameters:
density: 0.65
weight: 0.25
- model: MaziyarPanahi/Llama-3-8B-Instruct-v0.4
parameters:
density: 0.55
weight: 0.1
merge_method: dare_ties
base_model: KingNish/KingNish-Llama3-8b
parameters:
int8_mask: true
dtype: float16
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "KingNish/KingNish-Llama3-8b-v0.2-2"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.