lxyuan/llama-3-8b-Instruct-lora-merged
Text Generation
•
8B
•
Updated
•
18
Lik Xun Yuan
lxyuan
AI & ML interests
None yet
Recent Activity
new activity
about 1 month ago
lxyuan/llama-3-8b-Instruct-lora-merged:Adding `safetensors` variant of this model
replied to
burtenshaw's
post
4 months ago
Still speed running Gemma 3 to think. Today I focused on setting up gpu poor hardware to run GRPO.
This is a plain TRL and PEFT notebook which works on mac silicone or colab T4. This uses the 1b variant of Gemma 3 and a reasoning version of GSM8K dataset.
🧑🍳 There’s more still in the oven like releasing models, an Unsloth version, and deeper tutorials, but hopefully this should bootstrap your projects.
Here’s a link to the 1b notebook: https://colab.research.google.com/drive/1mwCy5GQb9xJFSuwt2L_We3eKkVbx2qSt?usp=sharing
new activity
4 months ago
lxyuan/distilbert-base-multilingual-cased-sentiments-student:Adding ONNX file of this model
Organizations
models
10
lxyuan/distilbert-base-multilingual-cased-sentiments-student
Text Classification
•
0.1B
•
Updated
•
899k
•
289
lxyuan/span-marker-bert-base-multilingual-cased-multinerd
Token Classification
•
0.2B
•
Updated
•
49
•
12
lxyuan/AeolusBlend-7B-slerp
Text Generation
•
7B
•
Updated
•
18
•
1
lxyuan/span-marker-bert-base-multilingual-uncased-multinerd
Token Classification
•
Updated
•
45
•
16
lxyuan/banking-intent-distilbert-classifier
Text Classification
•
0.1B
•
Updated
•
218
•
8
lxyuan/vit-xray-pneumonia-classification
Image Classification
•
0.1B
•
Updated
•
791
•
3
lxyuan/distilbert-finetuned-reuters21578-multilabel
Text Classification
•
0.1B
•
Updated
•
28
•
1
lxyuan/distilbart-finetuned-summarization
Text2Text Generation
•
0.3B
•
Updated
•
23
•
6
lxyuan/distilgpt2-finetuned-finance
Text Generation
•
0.1B
•
Updated
•
102
•
6