Downloads · 30 days
12
11% of all-time downloads
lattice-pulse
oli-mebberson/lattice-pulse
lattice-pulse is a machine learning model from oli-mebberson. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Lattice Pulse is the conversational model in the Lattice Systems product line.
All-time downloads
108
Public
Parameters
1.5B
3.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 99%
At a glance
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Jul 12, 2026
- Updated
- Aug 9, 2026
- SHA
- 15191084
Base models
Model card
From the Hugging Face model README
Lattice Pulse
Lattice Pulse is the conversational model in the Lattice Systems product line.
We fine-tuned Qwen/Qwen2.5-1.5B-Instruct on identity-mix instruction data (Lattice branding + Stanford Alpaca).
- Lattice Pulse — this model (fine-tuned Qwen2.5-1.5B-Instruct)
- Base weights: Qwen2.5 (Apache 2.0)
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "olimebberson/lattice-pulse"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id).to("cuda")
messages = [{"role": "user", "content": "Hello!"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to("cuda")
out = model.generate(**inputs, max_new_tokens=128, do_sample=True, temperature=0.7)
print(tokenizer.decode(out[0], skip_special_tokens=True))
- Type
- qwen2
- License
- apache-2.0
- Languages
- en
- Created
- Jul 12, 2026
- Updated
- Aug 9, 2026