Bobbie-model May 2026

Bobbie-model May 2026

They explicitly filtered out any data containing eval benchmark examples (MMLU, GSM8K, HumanEval) using 13-gram overlap detection. This means Bobbie's benchmarks are likely not contaminated. 4. Performance Benchmarks We ran Bobbie-7B-Instruct against Llama-3-8B-Instruct and Mistral-7B-v0.3 on an RTX 4090.

Published: April 13, 2026 | Reading time: 10 minutes bobbie-model

If you’ve been following the open-source LLM space, you’ve likely memorized the specs of Llama 3, Mixtral, and Qwen. But a new contender has been quietly gaining traction in the "small model" category: . They explicitly filtered out any data containing eval

messages = [ "role": "user", "content": "Summarize this 20k token document..." ] inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device) output = model.generate(inputs, max_new_tokens=512, temperature=0.7) print(tokenizer.decode(output[0][inputs.shape[1]:])) Bobbie works out-of-the-box with vLLM 0.6.0+: bobbie-model

They explicitly filtered out any data containing eval benchmark examples (MMLU, GSM8K, HumanEval) using 13-gram overlap detection. This means Bobbie's benchmarks are likely not contaminated. 4. Performance Benchmarks We ran Bobbie-7B-Instruct against Llama-3-8B-Instruct and Mistral-7B-v0.3 on an RTX 4090.

Published: April 13, 2026 | Reading time: 10 minutes

If you’ve been following the open-source LLM space, you’ve likely memorized the specs of Llama 3, Mixtral, and Qwen. But a new contender has been quietly gaining traction in the "small model" category: .

messages = [ "role": "user", "content": "Summarize this 20k token document..." ] inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device) output = model.generate(inputs, max_new_tokens=512, temperature=0.7) print(tokenizer.decode(output[0][inputs.shape[1]:])) Bobbie works out-of-the-box with vLLM 0.6.0+: