Muhammad Osama
mosama
AI & ML interests
None yet
Recent Activity
updated
a model
1 day ago
mosama/Qwen2.5-0.5B-Kaggle-Float16-Pretrained-arb-eng-urd-v2
updated
a model
1 day ago
mosama/Qwen2.5-0.5B-Kaggle-Float16-Pretrained-arb-eng-urd-v2
updated
a model
1 day ago
mosama/Qwen2.5-0.5B-Kaggle-Float16-Pretrained-arb-eng-urd-v2
Organizations
mosama's activity
tensor size mismatch
2
#9 opened 5 months ago
by
Daemontatox
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65e34821d821287383101b70/ftkiZCI7wcuVWB8ElGE39.jpeg)
Train Mistral 7B 0.2
9
#2 opened about 1 year ago
by
mosama
Error: `rope_scaling`must be a dictionary with two fields
6
#1 opened over 1 year ago
by
LeMoussel
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63cb7b071b705cc951ea5b82/ymRkw7ZThuKCWXQJBuVcr.png)
Model loading datatype bfloat16 or simple float16?
#2 opened about 1 year ago
by
mosama
With use_cache=False, the reponse is taking very long
#41 opened about 1 year ago
by
mosama
No chat template in tokenizer
2
#2 opened about 1 year ago
by
mosama
Output Score
4
#7 opened about 1 year ago
by
mosama