-
## Description
---
**Message from the maintainers**:
Love this enhancement proposal? Give it a 👍. We prioritise the proposals with the most 👍.
-
Add the option to load models in bfloat16 and float16. Esp important for large models like GPT-J and GPT-NeoX.
Ideally, load from HuggingFace in this low precision, do weight processing on the CPU,…
-
I am having trouble running your code to train GPT-J
I can't seem to find the proper value for model_name_or_path and base_model_path.
I have tried EleutherAI/gpt-j-6B for either of them but the p…
-
### Description
```shell
branch:main
docker_version:22.12
gpu: A5000
```
### Reproduced Steps
```shell
Created the docker image and installed gpt-j model.. the model runs and load and …
-
Goose AI offers API services for GPT Neo/GPT J and its much cheaper than OPEN AI. I don't have much experience on LLMs and I think the AI will be more based and sassy as I've seen from YouTube videos…
-
The output of gpt-j is very slow, for a 200 output token generation it takes about 20 minutes, for 2048 it takes more than an hour, this significantly limits any experimentation with the model.
I c…
ghost updated
2 years ago
-
gpt-j from ipex-llm/python/llm/example/GPU/HF-Transformers-AutoModels/Model/gpt-j
$ python generate.py
2024-03-31 17:42:23,819 - INFO - intel_extension_for_pytorch auto imported
2024-03-31 17:42:…
-
**Describe the bug**
I am using VS code insider in admin mode.
In backend .env I entered my AI keys:
OPENAI_API_KEY=sk-2siLny...
ANTHROPIC_API_KEY=sk-ant-api0...
When drag/drop an .mp4 vide…
-
Thanks so much for sharing your code.
I tested the local demo using 40 human-written stories (average length around 500 words) and got a few false alarms. 17 stories were flagged as having over a …
-
Is there any reason why we have an [accuracy upper limit for LLAMA2 Tokens per sample](https://github.com/mlcommons/inference/blob/master/tools/submission/submission_checker.py#L109) but not for GPT-J…