YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
MultiMash11-13B-slerp - GGUF
- Model creator: https://huggingface.co/allknowingroger/
- Original model: https://huggingface.co/allknowingroger/MultiMash11-13B-slerp/
Original model description:
tags: - merge - mergekit - lazymergekit - RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2 - Eurdem/megatron_2.1_MoE_2x7B base_model: - RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2 - Eurdem/megatron_2.1_MoE_2x7B license: apache-2.0
MultiMash11-13B-slerp
MultiMash11-13B-slerp is a merge of the following models using LazyMergekit:
𧩠Configuration
slices:
- sources:
- model: RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2
layer_range: [0, 32]
- model: Eurdem/megatron_2.1_MoE_2x7B
layer_range: [0, 32]
merge_method: slerp
base_model: RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "allknowingroger/MultiMash11-13B-slerp"
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
- 139