README.md

metadata

tags:
  - merge
  - mergekit
  - lazymergekit
  - not-for-all-audiences
license: llama3
language:
  - en
library_name: transformers
pipeline_tag: text-generation
base_model:
  - grimjim/Llama-3-Oasis-v1-OAS-8B
  - Hastagaras/Jamet-8B-L3-MK.V-Blackroot
  - Sao10K/L3-8B-Stheno-v3.2

Jamet-8B-Stheno-BlackOasis-8B-test001

Jamet-8B-Stheno-BlackOasis-8B-test001 is a merge of the following models using LazyMergekit:

• Sao10K/L3-8B-Stheno-v3.2
  • grimjim/Llama-3-Oasis-v1-OAS-8B
  • Hastagaras/Jamet-8B-L3-MK.V-Blackroot
  • Sao10K/L3-8B-Stheno-v3.2

🧩 Configuration

models:
  - model: grimjim/Llama-3-Oasis-v1-OAS-8B
  - model: Hastagaras/Jamet-8B-L3-MK.V-Blackroot
  - model: Sao10K/L3-8B-Stheno-v3.2
merge_method: model_stock
base_model: Sao10K/L3-8B-Stheno-v3.2
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Casual-Autopsy/Jamet-8B-Stheno-BlackOasis-8B-test001"
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"])