Downloads · 30 days
2
12% of all-time downloads
SpectraSuite_-_QuantLM_2.3B_4bit_Unpacked-awq
RichardErkhov/SpectraSuite_-_QuantLM_2.3B_4bit_Unpacked-awq
SpectraSuite_-_QuantLM_2.3B_4bit_Unpacked-awq is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
17
Public
Parameters
2.5B
1.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.6 GB · 100%
Parameter types
How the weights are stored.
I322.2B · 91%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
QuantLM_2.3B_4bit_Unpacked - AWQ
- Model creator: https://huggingface.co/SpectraSuite/
- Original model: https://huggingface.co/SpectraSuite/QuantLM_2.3B_4bit_Unpacked/
Original model description:
license: apache-2.0
QuantLM 2.3B 4 bit
QuantLM, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLM has the same architecture as LLaMa.
import transformers as tf, torch
model_name = "SpectraSuite/QuantLM_2.3B_4bit_Unpacked"
# Please adjust the temperature, repetition penalty, top_k, top_p and other sampling parameters according to your needs.
pipeline = tf.pipeline("text-generation", model=model_id, model_kwargs={"torch_dtype": torch.float16}, device_map="auto")
# These are base (pretrained) LLMs that are not instruction and chat tuned. You may need to adjust your prompt accordingly.
pipeline("Once upon a time")
- License: Apache 2.0
- We will use our GitHub repo for communication (including HF repo related queries). Feel free to open an issue here https://github.com/NolanoOrg/SpectraSuite
- Type
- llama
- Created
- Nov 27, 2024
- Updated
- Nov 27, 2024