Comments (6)
here's the performance:
LLaMA-7B | BPW | Wikitext2 |
---|---|---|
FP16 | 16 | 5.68 |
RTN | 4.00 | 6.29 |
RTN | 3.00 | 25.54 |
GPTQ-128g | 4.15 | 5.85 |
GPTQ-128g | 3.15 | 6.61 |
AWQ-128g | 4.15 | 5.81 |
AWQ-128g | 3.15 | 6.46 |
AWQ-32g | 3.60 | 6.10 |
SpQR-3b-16g-3b-32g-0.4% | 3.63 | 5.73 |
AWQ is more hardware efficient and simpler to implement than SpQR, but the compression ratio seems to be worse than SpQR.
from llm-awq.
Hi @loklok-infi,
Thanks for your interests in our work!
I think there are two potential reasons for the difference in the results:
(i) We used lm-eval-harness for evaluation, while GPTQ used their own implementation for evaluation (please refer here). There might be some differences in the experiment settings between them.
(ii) Regarding the 3/4-bit results, the results from GPTQ's paper are based on per-channel quantization without using group quantization. Our results are based on group quantization with a group size of 128.
Hope this answers your question :)
from llm-awq.
Hi @loklok-infi,
Thanks for your interests in our work! I think there are two potential reasons for the difference in the results: (i) We used lm-eval-harness for evaluation, while GPTQ used their own implementation for evaluation (please refer here). There might be some differences in the experiment settings between them. (ii) Regarding the 3/4-bit results, the results from GPTQ's paper are based on per-channel quantization without using group quantization. Our results are based on group quantization with a group size of 128. Hope this answers your question :)
Thank you for answering! Actually what confuses me more is the fp16 results are also ~10% different, but as you said I guess it's from the lm-eval-harness and the implementation of GPTQ.
I guess it's a problem for the whole community today, a similar problem seems happened between huggingface's LLM leaderboard and LLaMA's official result, hope soon we could have a one-true-standard benchmark implementation for LLMs.
from llm-awq.
here's the performance:
LLaMA-7B BPW Wikitext2
FP16 16 5.68
RTN 4.00 6.29
RTN 3.00 25.54
GPTQ-128g 4.15 5.85
GPTQ-128g 3.15 6.61
AWQ-128g 4.15 5.81
AWQ-128g 3.15 6.46
AWQ-32g 3.60 6.10
SpQR-3b-16g-3b-32g-0.4% 3.63 5.73
AWQ is more hardware efficient and simpler to implement than SpQR, but the compression ratio seems to be worse than SpQR.
Thank you! It's very helpful๐
from llm-awq.
here's the performance:
LLaMA-7B BPW Wikitext2
FP16 16 5.68
RTN 4.00 6.29
RTN 3.00 25.54
GPTQ-128g 4.15 5.85
GPTQ-128g 3.15 6.61
AWQ-128g 4.15 5.81
AWQ-128g 3.15 6.46
AWQ-32g 3.60 6.10
SpQR-3b-16g-3b-32g-0.4% 3.63 5.73
AWQ is more hardware efficient and simpler to implement than SpQR, but the compression ratio seems to be worse than SpQR.
Hey do you have a repo to benchmark all these quant methods?
from llm-awq.
here's the performance:
LLaMA-7B BPW Wikitext2
FP16 16 5.68
RTN 4.00 6.29
RTN 3.00 25.54
GPTQ-128g 4.15 5.85
GPTQ-128g 3.15 6.61
AWQ-128g 4.15 5.81
AWQ-128g 3.15 6.46
AWQ-32g 3.60 6.10
SpQR-3b-16g-3b-32g-0.4% 3.63 5.73
AWQ is more hardware efficient and simpler to implement than SpQR, but the compression ratio seems to be worse than SpQR.Hey do you have a repo to benchmark all these quant methods?
Yes , Code for this benchmark will be appreciated
from llm-awq.
Related Issues (20)
- awq_inference_engine is missing from source, so quantizing custom models fails HOT 2
- Support for Qwen models HOT 2
- AWQ for non-Transfomer Implementation HOT 3
- Error while Quantizing OWLv2 model
- No module named 'awq_inference_engine' HOT 2
- No such file or directory: "VILA1.5-13b-AWQ/llm/model-00001-of-00006.safetensors" HOT 8
- tinychat.serve.model_worker_new.py AWQ model in training mode
- how to support to custom module like mla in deep-seek-v2
- openAI-compatible tinychat API?
- AWQ kernel Issue
- Can you provide examples code to run inference on video QA? HOT 2
- AWQ and VILA dependency compatible issue HOT 2
- google.protobuf.message.DecodeError: Error parsing message HOT 1
- Is this a bug for the quantization phase? HOT 1
- Rocm support request
- Invalid Characters
- Memory increases significantly during inference
- Invalid Compute Capability when building Docker pytorch:23.12 HOT 1
- Request for Semi-Structured Sparse Matrix Support in AWQ Kernel
- Illegal memory access for LLama-3-70B
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from llm-awq.