-
Some commits lead to incorrect output of bitnet.
To reproduce:
```bash
python ./integration/BitNet/eval_correctness.py
```
The output is abnormal.
```
Replacing module layers.25.mlp.dow…
-
build_pytorch/pytorch/.venv/lib/python3.12/site-packages/bitnet-1.1-py3.12-linux-x86_64.egg/gemm_lowbit_ext.cpython-312-x86_64-linux-gnu.so: undefined symbol: _ZNK2at10TensorBase8data_ptrI6__halfEEPT_…
-
First of all, thanks. We need more ramps.
I was curious what you think of BitNet, and if llm.c is a place where experimenting with it could be facilitated. The papers were extremely promising and g…
-
Hi the bitnet paper looked promising, would the code be release? :)
-
The [Training Tips, Code and FAQ](https://github.com/microsoft/unilm/blob/master/bitnet/The-Era-of-1-bit-LLMs__Training_Tips_Code_FAQ.pdf) specifies that `BitLinear` has different `forward()` definiti…
-
# Bitnet 1.58 Groundwork
After some talks with Saroufim and the cuda mode team working on bitnet, we've outlined a strategy for implementing bitnet 1.58 method into torch. This issue lays the groun…
-
Hello.
First of all, thanks for sharing a bitnet training code.
I have a question about GPU memory usage.
As I understanding, bitnet can reduce VRAM usage compared to fp16/bf16 precision.
Howev…
-
-
Hi! I tried evaluating 1bitLLM/bitnet_b1_58-3B from hugging face. i am getting the error ValueError: Tokenizer class BitnetTokenizer does not exist or is not currently imported.
Kindly help!
```[tas…
-
Ref https://huggingface.co/papers/2310.11453