Downloads · 30 days
23
1% of all-time downloads
gpt-j-6b
d-matrix/gpt-j-6b
gpt-j-6b is a text generation model from d-matrix. Use it when you need the model to write or continue text. It is set up for transformers.
This is a d-Matrix functional reference of the MAIN model. The reference provides the following functional configurations: Configuration | Explanation :-- | :-- BASELINE | a reference functionally equivalent to the or…
All-time downloads
2.5K
Public
Repo size
72.6 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin24.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- gptj
- Access
- Public
- Created
- Feb 26, 2024
- Updated
- Jan 19, 2025
- SHA
- 19e1112a
Try a prompt
Model card
From the Hugging Face model README
This is a d-Matrix functional reference of the MAIN model. The reference provides the following functional configurations:
| Configuration | Explanation |
|---|---|
BASELINE | a reference functionally equivalent to the original model |
BASIC | all linear algebraic operands quantized to MXINT8-64, and all other operations transformed to approximated kernel simulations |
Usage
Install d-Matrix Dmx_Compressor first.
pip install dmx_compressor
The following is an example model and its evaluation.
git clone https://github.com/EleutherAI/lm-evaluation-harness
cd lm-evaluation-harness
pip install -e .
from dmx.compressor.modeling import DmxModel
import lm_eval
model_args = "pretrained=d-matrix/gpt-j-6b,trust_remote_code=True"
lm = lm_eval.api.registry.get_model("hf").create_from_arg_string(model_args, {"batch_size": 1})
# Transform the model with DMX
lm._model = DmxModel.from_torch(lm._model)
eval_results = lm_eval.evaluate(lm, lm_eval.tasks.get_task_dict(["wikitext"])) # Assign desired task, i.e. "wikitext"
- Task
- Text Generation
- Library
- transformers
- Type
- gptj
- Created
- Feb 26, 2024
- Updated
- Jan 19, 2025