lee/BitNet
1
0
Fork 0
mirror of https://github.com/microsoft/BitNet.git synced 2026-08-28 11:56:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

update README

Browse Source
This commit is contained in:
Eddie-Wang1120
2025-02-16 15:07:08 +08:00
parent 4c736e3728
commit 61e37b5430
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -2
View File
@@ -160,7 +160,7 @@ huggingface-cli download 1bitLLM/bitnet_b1_58-large --local-dir models/bitnet_b1
python setup_env.py -md models/bitnet_b1_58-large -q i2_s
```
<pre>
usage: setup_env.py [-h] [--hf-repo {1bitLLM/bitnet_b1_58-large,1bitLLM/bitnet_b1_58-3B,HF1BitLLM/Llama3-8B-1.58-100B-tokens,tiiuae/Falcon3-1B-Instruct-1.58bit,tiiuae/Falcon3-3B-Instruct-1.58bit,tiiuae/Falcon3-7B-Instruct-1.58bit,tiiuae/Falcon3-10B-Instruct-1.58bit}] [--model-dir MODEL_DIR] [--log-dir LOG_DIR] [--quant-type {i2_s,tl1}] [--quant-embd]
usage: setup_env.py [-h] [--hf-repo {1bitLLM/bitnet_b1_58-large,1bitLLM/bitnet_b1_58-3B,HF1BitLLM/Llama3-8B-1.58-100B-tokens,tiiuae/Falcon3-1B-Instruct-1.58bit,tiiuae/Falcon3-3B-Instruct-1.58bit,tiiuae/Falcon3-7B-Instruct-1.58bit,tiiuae/Falcon3-10B-Instruct-1.58bit}] [--model-dir MODEL_DIR] [--log-dir LOG_DIR] [--quant-type {i2_s,tl1,tl2,tl2-loss}] [--quant-embd]
[--use-pretuned]
Setup the environment for running inference
@@ -173,7 +173,7 @@ optional arguments:
Directory to save/load the model
--log-dir LOG_DIR, -ld LOG_DIR
Directory to save the logging info
--quant-type {i2_s,tl1}, -q {i2_s,tl1}
--quant-type {i2_s,tl1,tl2,tl2-loss}, -q {i2_s,tl1,tl2,tl2-loss}
Quantization type
--quant-embd Quantize the embeddings to f16
--use-pretuned, -p Use the pretuned kernel parameters