Hugging Face's logo
antony's picture
14 1 1

antony

antony-pk
·

AI & ML interests

None yet

Recent Activity

New activity about 1 month ago
meta-llama/Llama-3.1-8B-Instruct:Full SFT training caused lose its foundational capabilities
updated a collection about 2 months ago
Llama 3.2
updated a collection 2 months ago
Qwen-2.5
View all activity

Organizations

Soft Suave Pvt Ltd's profile picture Softsuave Technologies's profile picture

antony-pk's activity

New activity in meta-llama/Llama-3.1-8B-Instruct about 1 month ago

Full SFT training caused lose its foundational capabilities

10
#71 opened 4 months ago by sinlew
New activity in unsloth/Qwen2.5-0.5B 2 months ago

Invalid script is provided
#1 opened 2 months ago by antony-pk
New activity in stabilityai/stable-diffusion-x4-upscaler 2 months ago

Cuda Out of Memory

1
#23 opened over 1 year ago by xings19
New activity in meta-llama/Llama-3.1-8B-Instruct 4 months ago

Request: DOI

1
#85 opened 4 months ago by moh996

Request: DOI

1
#86 opened 4 months ago by sanjeev929

Tokenizer padding token

1
#76 opened 4 months ago by Rish1

Minimum gpu ram capacity

10
#77 opened 4 months ago by bob-sj

Efficiency low after adding the adapter_model.safetensors with base model
#78 opened 4 months ago by antony-pk

Inference endpoint deployment for 'meta-llama/Meta-Llama-3.1-8B-Instruct' fails

6
#62 opened 4 months ago by Keertiraj
New activity in NousResearch/Yarn-Llama-2-7b-64k 4 months ago

Error: `rope_scaling`must be a dictionary with two fields

6
#1 opened about 1 year ago by LeMoussel
New activity in hiyouga/Baichuan-7B-sft 4 months ago

We need an `offload_dir` to dispatch this model according to this `device_map`

3
#3 opened over 1 year ago by littleevillin