llm-awq
SqueezeLLM
| llm-awq | SqueezeLLM | |
|---|---|---|
| 7 | 5 | |
| 1,902 | 573 | |
| 10.9% | 4.0% | |
| 8.0 | 6.9 | |
| 8 days ago | 19 days ago | |
| Python | Python | |
| MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
llm-awq
-
TinyChat: Large Language Model on the Edge
TinyChat is an efficient, lightweight, Python-native serving framework for 4-bit LLMs by AWQ. It delivers 2.3x generation speed up on RTX4090.
Code: https://github.com/mit-han-lab/llm-awq/tree/main/tinychat
- FLaNK Stack Weekly 23 Oct 2023
-
New base model InternLM 7B weights released, with 8k context window.
I am having trouble finding any 8bit GPTQ models at all, there don't seem to be any on HF it's almost all 4bit with the odd 3bit of the big ones. Suspect I will have to make my own for eval purposes but it's lower priority on my list then finding a 4bit that's GPU friendly but doesn't have such a performance penalty... Looking at AWQ they have 3 and 4bit versions.
-
Llama33B vs Falcon40B vs MPT30B
Using the currently popular gptq the 3bit quantization hurts performance much more than 4bit, but there's also awq (https://github.com/mit-han-lab/llm-awq) and squishllm (https://github.com/SqueezeAILab/SqueezeLLM) which are able to manage 3bit without as much performance drop - I hope to see them used more commonly.
- New hardware-friendly quantization method
-
Activation-Aware Weight Quantization for LLM Compression Outperforms GPTQ
Better quantization would have a direct and meaningful impact for everyone running local LLMs. The technique has already been applied to both Vicuna and the multimodal LLaMA variant LLaVA.
https://github.com/mit-han-lab/llm-awq
-
New quantization method AWQ outperforms GPTQ in 4-bit and 3-bit with 1.45x speedup and works with multimodal LLMs
GitHub: https://github.com/mit-han-lab/llm-awq
SqueezeLLM
-
Llama33B vs Falcon40B vs MPT30B
Using the currently popular gptq the 3bit quantization hurts performance much more than 4bit, but there's also awq (https://github.com/mit-han-lab/llm-awq) and squishllm (https://github.com/SqueezeAILab/SqueezeLLM) which are able to manage 3bit without as much performance drop - I hope to see them used more commonly.
-
Has anyone tried out Squeezellm?
[Paper][Github][Model]
- SqueezeLLM: Dense-and-Sparse Quantization
- New quantization method SqueezeLLM allows for loseless compression for 3-bit and outperforms GPTQ and AWQ in both 3-bit and 4-bit. Quantized Vicuna and LLaMA models have been released.
What are some alternatives?
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
Qwen-7B - The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud. [Moved to: https://github.com/QwenLM/Qwen]
Voyager - An Open-Ended Embodied Agent with Large Language Models
Qwen - The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
langchain4j-examples
Pretrained-Language-Model - Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
CML_AMP_AI_Text_Summarization_with_Amazon_Bedrock - CML_AMP_AI_Text_Summarization_with_Amazon_Bedrock
GoLLIE - Guideline following Large Language Model for Information Extraction
kafka-streams-dashboards - showcases Grafana dashboards for Kafka Stream applications leveraging client JMX metrics.
LLMCompiler - [ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
data-in-motion - This is repository for tutorials of Data In Motion starting with Data Distribution
LocalMentor - Local Startup Advisor Chatbot