Fine-tuning LLMs to 1.58bit: extreme quantization made easy
•
202
Mohamed Mekkouri
medmekk
AI & ML interests
None yet
Recent Activity
liked
a model
12 days ago
HF1BitLLM/Llama3-8B-1.58-100B-tokens
New activity
17 days ago
HF1BitLLM/README
New activity
21 days ago
HF1BitLLM/Llama3-8B-1.58-100B-tokens
Articles
Organizations
spaces
3
models
37
medmekk/Llama3.1-70B-GPTQ-4bits
Text Generation
•
Updated
•
25
medmekk/smollm-360M-instruct-new-1
Updated
medmekk/smollm-360M-instruct-new
Updated
medmekk/Llama3.2-1B-GPTQ-4bits-2
Text Generation
•
Updated
•
10
medmekk/Llama3.2-1B-GPTQ-4bits
Text Generation
•
Updated
•
17
medmekk/quantized-llama-70B
Text Generation
•
Updated
•
22
medmekk/testing_repo_name
Updated
•
7
medmekk/deepseek-coder-1.3b-base-torchao-int8_weight_only
Updated
•
6
medmekk/custom_name_1
Updated
•
4
medmekk/custom_name
Updated
•
3
datasets
None public yet