galqiwi/llama-3.2-3b-aqlm-pv-2x8-f32-int8-and-nf4-emb
Updated
Vladimir
galqiwi
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
Quartet: Native FP4 Training Can Be Optimal for Large Language Models
upvoted
a
paper
3 months ago
Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
upvoted
an
article
4 months ago
Digest of models based on YandexGPT 5 Lite
Organizations
galqiwi/llama-3.2-1b-aqlm-pv-2x8-f32-int8-and-nf4-emb
Updated
galqiwi/cv-2024
Updated
galqiwi/llama-3.1-aqlm-pv-2x8-f32-int8-and-nf4-emb
Updated
galqiwi/llama3.1-8b-instruct-nf4-64
8B
•
Updated
•
19
galqiwi/llama3.1-8b-instruct-nf4-1024
8B
•
Updated
•
6
galqiwi/llama3.1-8b-instruct-nf3-64
8B
•
Updated
•
26
galqiwi/llama3.1-8b-instruct-nf3-1024
8B
•
Updated
•
15
galqiwi/llama3.1-8b-instruct-af4-64
8B
•
Updated
•
9
galqiwi/llama3.1-8b-instruct-af4-1024
8B
•
Updated
•
7
galqiwi/llama3.1-8b-instruct-af3-64
8B
•
Updated
•
6
galqiwi/llama2-70b-hf
69B
•
Updated
•
6
galqiwi/Llama-2-7b-hf
7B
•
Updated
•
6
galqiwi/Meta-Llama-3-70B-AQLM-PV-1Bit-1x16
Updated
galqiwi/llama-3.1-aqlm-pv-2x8-f32-int8-emb
Updated
galqiwi/llama-3.1-aqlm-pv-2x8-f32-sliced-embedding
Updated
galqiwi/Meta-Llama-3.1-8B-AQLM-2x8g8-NO-TUNE
3B
•
Updated
•
7
galqiwi/test
Updated
galqiwi/test-upload
Text Generation
•
1B
•
Updated
•
14