L3-15B-Stheno-passthrough
L3-15B-Stheno-passthrough is a merge of the following models using LazyMergekit:
🧩 Configuration
slices:
- sources:
- layer_range: [0, 24]
model: Sao10K/L3-8B-Stheno-v3.2
- sources:
- layer_range: [8, 24]
model: Sao10K/L3-8B-Stheno-v3.2
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [8, 24]
model: Sao10K/L3-8B-Stheno-v3.1
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- layer_range: [24, 32]
model: Sao10K/L3-8B-Stheno-v3.1
dtype: bfloat16
merge_method: passthrough
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "jsfs11/L3-15B-Stheno-passthrough"
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"])