ChatBit
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Beijing Institute of Technology,Academy of Military Science,Minzu University of China
- Organisation type
- Academia,Government,Academia
- Country
- China
- Published
- 28 June 2024
- Authors
- Zhang Huaping, Li Chunjin, Wei Shunping, Geng Guotong, Li Weiwei, Li Yugang
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Chat, Language modeling/generation
- Base model
- LLaMA-13B
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 13B
- Training data
- 100,000,000 tokens
- Epochs
- 3
- Batch size
- 16,384
Assuming as in LLaMA-13 since it is its finetune
"researchers noted that its model incorporated only 100,000 military dialogue records, a relatively small number compared with other LLMs." "其他设置：训练的epoch为3，最大长度 max_length为2 048，batch_size为8，使用8个 A100 GPU训练，梯度积累为4，warm_up为训 练总步数的10%，采用AdamW优化器， 1 = 0.90、 2 = 0.95，学习率为1e-5" which is translated as "Other settings: 3 epochs for training, max_length of 2 048, batch_size of 8, 8 A100 GPUs for training, gradient accumulation of 4, warm_up of 10% of the total number of training steps, AdamW optim…
max_length of 2 048, batch_size of 8
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- How it was established
- Operation counting
- Fine-tuning compute
- 2.3 × 10¹⁹ FLOP
6ND = 6*13*10^9*100000000*3 = 2.34e+19
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA A100
- Chips used
- 8
- Power draw
- 6.3 kW
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- Large language model-driven open-source intelligence cognition
- Last updated
- 28 November 2025
What the numbers mean
What this model is
ChatBit was published by Beijing Institute of Technology,Academy of Military Science,Minzu University of China, in China, in June 2024. academia,Government,Academia is the category the publisher falls under.
It works in Language, and is recorded as doing chat, Language modeling/generation.
It is derived from LLaMA-13B rather than trained from scratch, which is the usual way a specialised model is produced.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
The training set ran to roughly 100,000,000 tokens.
Answers
ChatBit — common questions
When was ChatBit released?
ChatBit was published in June 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is ChatBit used for?
ChatBit works in Language, and is recorded as handling chat, Language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run ChatBit?
None. ChatBit is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Is ChatBit open source?
No. ChatBit has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does ChatBit have?
ChatBit has 13B parameters. Assuming as in LLaMA-13 since it is its finetune. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
Who created ChatBit?
ChatBit was published by Beijing Institute of Technology,Academy of Military Science,Minzu University of China, based in China, categorised as academia,Government,Academia.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.