Downloads · 30 days
21
5% of all-time downloads
TRagx-GPTQ-internlm2-7b
rayliuca/TRagx-GPTQ-internlm2-7b
TRagx-GPTQ-internlm2-7b is a text generation model from rayliuca. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Merged and GPTQ quantized version of rayliuca/TRagx-internlm2-7b
All-time downloads
391
Public
Parameters
7.7B
5.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.1 GB · 100%
Parameter types
How the weights are stored.
I327B · 90%
Try a prompt
Model card
From the Hugging Face model README
Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->Merged and GPTQ quantized version of rayliuca/TRagx-internlm2-7b
Note: I'm having some difficulties quantizing the models using GPTQ. Mistral and NeuralOmniBeagle's GPTQ models have significantly degraded output, while quantized TowerInstruct v0.2 was not working out right
While this quantized model for InternLM2 seems to work all right, the translation accuracy is not validated.
These AWQ quantized models are recommended:
GPTQ Dataset
Qutanized with nsamples=45 * 3 languages [ja, zh, en] from the c4 dataset
License
See the original InternLM2 repo https://huggingface.co/internlm/internlm2-7b#open-source-license
- Task
- Text Generation
- Library
- transformers
- Type
- internlm2
- License
- apache-2.0
- Languages
- en, ja, zh
- Created
- Feb 22, 2024
- Updated
- Feb 23, 2024