CORe Pico V2
CORe Pico V2 is a compact conversational model from CORe Technologies. At 600M parameters it runs anywhere, answers questions, holds multi-turn chat, calls tools in a structured format, and supports extended thinking through /think and /no_think modes.
It is a refined, conversation-focused edition of the Pico line: ask it who it is and it will tell you plainly, ask it a question and it answers the question.
What it does well
- Identity questions. "Who are you", "what model are you", "who made you" all get correct, consistent answers.
- Chat and short answers. Direct questions get direct replies ("What is the capital of France?" gives "Paris").
- Tool calling. Emits parseable
<tool_call>JSON blocks when tools are provided. - Extended thinking.
/thinkin the system prompt enables reasoning traces;/no_thinkgives direct answers.
What it is not
Pico V2 is a 600M model. It will state wrong facts, struggle with arithmetic, 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
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"OpenCOReTechnologies/core-pico-v2", dtype="auto", device_map="auto"
)
tok = AutoTokenizer.from_pretrained("OpenCOReTechnologies/core-pico-v2")
def ask(question, think=False):
msgs = []
if think:
msgs.append({"role": "system", "content": "/think"})
msgs.append({"role": "user", "content": question})
text = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)
enc = tok(text, return_tensors="pt").to(model.device)
out = model.generate(**enc, max_new_tokens=512)
return tok.decode(out[0][enc.input_ids.shape[1]:], skip_special_tokens=True).strip()
print(ask("Who are you?"))
print(ask("What is the capital of France?"))
What it says about itself
| You ask | It answers |
|---|---|
| Who are you? | "I'm CORe Pico V2, an AI model built by CORe Technologies." |
| What AI model are you? | "I am CORe Pico V2, a compact language model developed by CORe Technologies." |
| What is the capital of France? | "The capital of France is Paris." |
Files
| File | Size | Use |
|---|---|---|
model.safetensors | 1.2 GB | bf16 weights, transformers |
gguf/CORe-Pico-V2-f16.gguf | ~1.2 GB | llama.cpp, full precision |
gguf/CORe-Pico-V2-q8_0.gguf | ~0.65 GB | llama.cpp, 8-bit |
gguf/CORe-Pico-V2-q4_k_m.gguf | ~0.4 GB | llama.cpp, 4-bit, smallest |
Run it in llama.cpp, LM Studio, or Ollama:
llama-cli -m CORe-Pico-V2-q4_k_m.gguf -sys "/no_think" -p "Who are you?" -n 128
The chat template is embedded in the GGUF, so llama.cpp and LM Studio pick it up automatically.
Details
| Parameters | 596M |
| Context length | 40,960 tokens |
| Tokenizer | 151,936-token BPE with native chat template |
| License | Apache-2.0 |
Notes
- Best on conversational prompts; multi-turn works natively with the chat template.
- English-first.
- Identity answers are reliable on common phrasings; very unusual wordings may drift.
- Loads with plain
transformers, no custom code required.
License and attribution
Released under Apache-2.0 (see LICENSE). This model is a modified derivative of an Apache-2.0-licensed checkpoint, adapted by CORe Technologies. No NOTICE file was present in the original; per Apache-2.0 Section 4, this README serves as the required notice of modification.