Qwen/Qwen2.5-1.5B-Instruct
Text Generation
•
Updated
•
7M
•
•
248
Arjun Srivastava
arjunsriva
·
AI & ML interests
Recommendation Engines, Causal Inference
Recent Activity
liked
a model
10 days ago
Qwen/Qwen2.5-1.5B-Instruct
liked
a model
12 days ago
tencent/HunyuanVideo
liked
a model
30 days ago
microsoft/OmniParser
Organizations
arjunsriva's activity
liked
a
model
10 days ago
liked
a
model
12 days ago
liked
a
model
30 days ago
liked
a
dataset
4 months ago
liked
a
model
4 months ago
liked
2
models
6 months ago
liked
2
datasets
8 months ago
liked
5
models
8 months ago
NexaAIDev/Octopus-v2
Text Generation
•
Updated
•
504
•
867
stabilityai/stablelm-2-12b-chat
Text Generation
•
Updated
•
3.72k
•
86
mlx-community/dolphin-2.2-yi-34b-200k-4bit
Updated
•
9
•
1
CohereForAI/c4ai-command-r-plus-4bit
Text Generation
•
Updated
•
464
•
247
CohereForAI/c4ai-command-r-plus
Text Generation
•
Updated
•
3.39k
•
1.7k
upvoted
a
paper
8 months ago
liked
a
dataset
8 months ago
reacted to
akhaliq's
post with 👍
10 months ago
Post
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits (2402.17764)
Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs). In this work, we introduce a 1-bit LLM variant, namely BitNet b1.58, in which every single parameter (or weight) of the LLM is ternary {-1, 0, 1}. It matches the full-precision (i.e., FP16 or BF16) Transformer LLM with the same model size and training tokens in terms of both perplexity and end-task performance, while being significantly more cost-effective in terms of latency, memory, throughput, and energy consumption. More profoundly, the 1.58-bit LLM defines a new scaling law and recipe for training new generations of LLMs that are both high-performance and cost-effective. Furthermore, it enables a new computation paradigm and opens the door for designing specific hardware optimized for 1-bit LLMs.
The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits (2402.17764)
Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs). In this work, we introduce a 1-bit LLM variant, namely BitNet b1.58, in which every single parameter (or weight) of the LLM is ternary {-1, 0, 1}. It matches the full-precision (i.e., FP16 or BF16) Transformer LLM with the same model size and training tokens in terms of both perplexity and end-task performance, while being significantly more cost-effective in terms of latency, memory, throughput, and energy consumption. More profoundly, the 1.58-bit LLM defines a new scaling law and recipe for training new generations of LLMs that are both high-performance and cost-effective. Furthermore, it enables a new computation paradigm and opens the door for designing specific hardware optimized for 1-bit LLMs.