Ivme-Conversate-N-v2-Instruct

9,021,600 parameters. Standard decoder-only Transformer (tied embeddings, multi-head attention, RoPE, SwiGLU, RMSNorm) -- matching Ivme-Conversate-v2-Base's proven recipe exactly, deliberately with zero architectural novelty.

Trained single-epoch on ~900M tokens, instruct-heavy from the start rather than base-pretrain-then-finetune: UltraChat-200k (real multi-turn dialogue) as the dominant 45% share, plus SODA, UltraInteract reasoning traces, orca-math, dolly-15k instructions, and sql-create-context. All sources permissively licensed (MIT/CC-BY/CC-BY-SA).

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "ivmelabs/Ivme-Conversate-N-v2-Instruct", trust_remote_code=True
)
tok = AutoTokenizer.from_pretrained("ivmelabs/Ivme-Conversate-N-v2-Instruct")

ids = tok("Hello!", return_tensors="pt").input_ids
out = model.generate(ids, max_new_tokens=80, do_sample=True, temperature=0.8, top_k=40)
print(tok.decode(out[0]))

Note: no KV-cache in this architecture -- .generate() works but is O(n^2) rather than O(n), fine for short samples, not tuned for long-form serving.