MergeTrix-7B is a merge of the following models using LazyMergekit:
MergeTrix-7B-GGUF
Quantisized versions of MergeTrix-7B. Supports:
- mergetrix-7b.Q4_K_M.gguf (4.37GB): medium, balanced quality
- mergetrix-7b.Q5_K_S.gguf (5 GB): large, low quality loss
- mergetrix-7b.Q5_K_M.gguf (5.13 GB): large, very low quality loss
- mergetrix-7b.Q6_K.gguf (5.94 GB): very large, extremely low quality loss
𧩠Configuration
models:
- model: udkai/Turdus
# No parameters necessary for base model
- model: abideen/NexoNimbus-7B
parameters:
density: 0.53
weight: 0.4
- model: fblgit/UNA-TheBeagle-7b-v1
parameters:
density: 0.53
weight: 0.3
- model: argilla/distilabeled-Marcoro14-7B-slerp
parameters:
density: 0.53
weight: 0.3
merge_method: dare_ties
base_model: udkai/Turdus
parameters:
int8_mask: true
dtype: bfloat16
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "CultriX/MergeTrix-7B"
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
- 76