Quantized Llama models in 2,4, and 8 bit versions
Divyanshu Kumar
divyanshusingh
AI & ML interests
NLP, CV, Federated Learning
Recent Activity
published
a model
about 12 hours ago
divyanshusingh/DeepSeek-R1-Distill-Qwen-7B-G1-CoT-SFT
new activity
5 days ago
google/gemma-3n-E4B-it:Update config.json
updated
a model
19 days ago
divyanshusingh/DeepSeek-R1-0528-Qwen3-8B-G1-SFT
Organizations
models
16
divyanshusingh/DeepSeek-R1-0528-Qwen3-8B-G1-SFT
8B
•
Updated
•
19
divyanshusingh/DeepSeek-R1-0528-Qwen3-8B-G1-CoT-SFT
8B
•
Updated
•
6
divyanshusingh/DeepSeek-R1-Distill-Qwen-7B-G1-CoT-SFT
8B
•
Updated
•
5
divyanshusingh/Llama-3.1-8B-LoRA-G1
Updated
•
14
divyanshusingh/Mistral-7B-Instruct-v0.2-GGUF
7B
•
Updated
•
21
divyanshusingh/Mistral-7B-Instruct-v0.3-GGUF
7B
•
Updated
•
30
divyanshusingh/Mistral-Nemo-Instruct-2407-GGUF
12B
•
Updated
•
26
divyanshusingh/Mistral-7B-Instruct-v0.1-GGUF
7B
•
Updated
•
27
divyanshusingh/Llama-2-7b-chat-GGUF
7B
•
Updated
•
31
divyanshusingh/CodeLlama-7b-GGUF
7B
•
Updated
•
30
datasets
0
None public yet