Hivemind-32B-Preview is a 32B-parameter model fine-tuned for multi-turn, emotionally attentive conversation in human-facing enterprise contexts. It is built on Qwen3-32B with a training set focused on conversational depth, emotional subtext, and sustained engagement across complex interpersonal scenarios.
Hivemind-32B-Preview was fine-tuned for multi-turn, human-facing conversations involving ambiguity and emotional subtext. The training set was purpose-built from enterprise interaction data.
Hivemind-32B-Preview is designed for enterprise human-agent partnership contexts: customer support, coaching-style interactions, and similar conversational deployments where sustained emotional attentiveness matters.
Hivemind-32B-Preview is a preview release. As with any conversational model, it has scope boundaries we are actively refining:
We welcome failure-case reports from researchers and deployment partners at
contact@hivelabs.dev.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model_id = "HiveLabsAI/hivemind-32b-preview"
4tokenizer = AutoTokenizer.from_pretrained(model_id)
5model = AutoModelForCausalLM.from_pretrained(
6 model_id,
7 torch_dtype="bfloat16",
8 device_map="auto",
9)
10
11messages = [{"role": "user", "content": "Your message here"}]
12inputs = tokenizer.apply_chat_template(
13 messages, return_tensors="pt", add_generation_prompt=True
14).to(model.device)
15outputs = model.generate(
16 inputs, max_new_tokens=2048, temperature=0.6, top_p=0.95, top_k=20
17)
18print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))
Hivemind is developed by
Hive Labs. For research collaboration, deployment questions, or to report failure cases, contact
contact@hivelabs.dev.
