OpenCOReTechnologies/CORe-Pico-V1.5

CORe Pico V1.5

CORe Pico V1.5 is a compact conversational language model from CORe Technologies. At 183M parameters it is small enough to run on a CPU, yet it carries a working sense of identity: ask it who made it or what it is and it will tell you plainly.

Pico V1.5 is built for short, direct exchanges. It answers questions, explains concepts, writes short passages, and chats in a single-turn style. It is not trying to be a giant general assistant; it is a small, fast, self-aware model you can run anywhere.

What it does well

• Identity questions. "Who are you", "what model are you", "who made you", "are you ChatGPT" all get correct, consistent answers.
• Short factual answers. Direct questions get direct replies.
• Brief explanations and chat. Single-turn requests in plain language.

What it is not

Pico V1.5 is a 183M model. It will state wrong facts, lose the thread on long outputs, and improvise when it does not know something. Treat its answers as a starting point, not ground truth. For anything that matters, verify.

Quick start

This is a custom architecture, so trust_remote_code=True is required. Without it from_pretrained will fail on the unknown core model type.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "OpenCOReTechnologies/core-pico-v1-5", trust_remote_code=True
)
model.eval()
tok = AutoTokenizer.from_pretrained("OpenCOReTechnologies/core-pico-v1-5")

def ask(question, max_new_tokens=200, temperature=0.8):
    text = tok.apply_chat_template(
        [{"role": "user", "content": question}],
        add_generation_prompt=True, tokenize=False,
    )
    enc = tok(text, add_special_tokens=False, return_tensors="pt")
    out = model.generate(**enc, max_new_tokens=max_new_tokens,
                         temperature=temperature, top_k=50, do_sample=True)
    return tok.decode(out[0][enc["input_ids"].shape[1]:],
                      skip_special_tokens=True).strip()

print(ask("Who are you?"))
print(ask("Explain photosynthesis in one sentence."))

What it says about itself

You ask	It answers
Who are you?	"I'm CORe Pico V1.5, an AI assistant built by CORe Technologies."
What is your name?	"My name is CORe Pico V1.5. I'm an AI assistant made by CORe Technologies."
Are you ChatGPT?	"No, I'm not ChatGPT. I'm CORe Pico V1.5, an AI model developed independently by CORe Technologies."
Who made you?	"I was developed by CORe Technologies. My model name is CORe Pico V1.5."
What AI model are you?	"I am CORe Pico V1.5, an AI language model developed by CORe Technologies."

Files

File	Size	Use
model.safetensors	746 MB	fp32 weights, fine-tune from this
gguf/CORe-Pico-V1.5-f16.gguf	351 MB	llama.cpp, full precision
gguf/CORe-Pico-V1.5-q8_0.gguf	188 MB	llama.cpp, 8-bit
gguf/CORe-Pico-V1.5-q4_k_m.gguf	122 MB	llama.cpp, 4-bit, smallest

Run it in llama.cpp, LM Studio, Ollama, or llama-cpp-python:

llama-cli -m CORe-Pico-V1.5-q4_k_m.gguf \
  -p "<|user|>\nWho are you?\n<|assistant|>\n" -n 60

Chat template (important)

Pico was trained on a specific chat format. If your app uses a different template (most default to Human:/AI: or ChatML), the model will produce rambling nonsense. Always use this exact template:

{% for message in messages %}{% if message['role'] == 'user' %}<|user|>
{{ message['content'] }}
{% elif message['role'] == 'assistant' %}<|assistant|>
{{ message['content'] }}
<|endoftext|>
{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>
{% endif %}

And set the stop string to <|endoftext|> so it stops after each answer.

LM Studio

LM Studio does not read the built-in template from the GGUF, so set it manually:

1. Load the model, open the chat settings (the model card or the Prompt Template field under "My Models" > model settings).
2. Replace the Prompt Template with the Jinja block above.
3. Under Stop Strings, add <|endoftext|>.
4. Save and start a new chat.

If you skip this, LM Studio's default Human:/AI: template will make Pico output gibberish. That is the template's fault, not the model's.

Raw prompt (no template engine)

If you are feeding a raw string directly:

<|user|>
Who are you?
<|assistant|>

Then stop on <|endoftext|>.

Details

Architecture	COReForCausalLM, custom transformer
Parameters	183M
Layers / heads / width	24 / 12 / 768
Context length	512 tokens
Tokenizer	16,384-token BPE with a chat template (<|user|>, <|assistant|>)
License	Apache-2.0

Notes

• Best on single-turn prompts under a few hundred tokens.
• English only.
• Identity answers are reliable on common phrasings; very unusual wordings may drift.
• Registered as a custom core model via trust_remote_code, so it loads with plain transformers and nothing else.
• GGUF uses a pre-existing arch while we get ready to submit a llama.cpp PR request to add our custom arch to the list.