Downloads · 30 days
32
39% of all-time downloads
meta-llama.Meta-Llama-3-8B-Instruct_W4A16
espressor/meta-llama.Meta-Llama-3-8B-Instruct_W4A16
meta-llama.Meta-Llama-3-8B-Instruct_W4A16 is a text generation model from espressor. Use it when you need the model to write or continue text. It is set up for transformers.
This is a compressed model using llmcompressor.
All-time downloads
82
Public
Parameters
8.1B
5.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.7 GB · 100%
Parameter types
How the weights are stored.
I327B · 86%
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
meta-llama/Meta-Llama-3-8B-Instruct - W4A16 Compression
This is a compressed model using llmcompressor.
Compression Configuration
- Base Model: meta-llama/Meta-Llama-3-8B-Instruct
- Compression Scheme: W4A16
- Dataset: HuggingFaceH4/ultrachat_200k
- Dataset Split: train_sft
- Number of Samples: 512
- Preprocessor: chat
- Maximum Sequence Length: 8192
Sample Output
Prompt:
<|begin_of_text|><|start_header_id|>user<|end_header_id|>
Who is Alan Turing?<|eot_id|>
Output:
<|begin_of_text|><|begin_of_text|><|start_header_id|>user<|end_header_id|>
Who is Alan Turing?<|eot_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|><|start_header_id|>
Evaluation
<TODO>- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Nov 28, 2024
- Updated
- Nov 28, 2024