from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
model_path = "solidrust/DeepMagic-Coder-7b-Alt-AWQ"
system_message = "You are DeepMagic-Coder-7b-Alt, incarnated as a powerful AI. You were created by rombodawg."# Load model
model = AutoAWQForCausalLM.from_quantized(model_path,
fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(model_path,
trust_remote_code=True)
streamer = TextStreamer(tokenizer,
skip_prompt=True,
skip_special_tokens=True)
# Convert prompt to tokens
prompt_template = """\<|im_start|>system{system_message}<|im_end|><|im_start|>user{prompt}<|im_end|><|im_start|>assistant"""
prompt = "You're standing on the surface of the Earth. "\
"You walk one mile south, one mile west and one mile north. "\
"You end up exactly where you started. Where are you?"
tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
return_tensors='pt').input_ids.cuda()
# Generate output
generation_output = model.generate(tokens,
streamer=streamer,
max_new_tokens=512)
About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
Runs of solidrust DeepMagic-Coder-7b-Alt-AWQ on huggingface.co
22
Total runs
0
24-hour runs
-1
3-day runs
3
7-day runs
10
30-day runs
More Information About DeepMagic-Coder-7b-Alt-AWQ huggingface.co Model
DeepMagic-Coder-7b-Alt-AWQ huggingface.co
DeepMagic-Coder-7b-Alt-AWQ huggingface.co is an AI model on huggingface.co that provides DeepMagic-Coder-7b-Alt-AWQ's model effect (), which can be used instantly with this solidrust DeepMagic-Coder-7b-Alt-AWQ model. huggingface.co supports a free trial of the DeepMagic-Coder-7b-Alt-AWQ model, and also provides paid use of the DeepMagic-Coder-7b-Alt-AWQ. Support call DeepMagic-Coder-7b-Alt-AWQ model through api, including Node.js, Python, http.
DeepMagic-Coder-7b-Alt-AWQ huggingface.co is an online trial and call api platform, which integrates DeepMagic-Coder-7b-Alt-AWQ's modeling effects, including api services, and provides a free online trial of DeepMagic-Coder-7b-Alt-AWQ, you can try DeepMagic-Coder-7b-Alt-AWQ online for free by clicking the link below.
solidrust DeepMagic-Coder-7b-Alt-AWQ online free url in huggingface.co:
DeepMagic-Coder-7b-Alt-AWQ is an open source model from GitHub that offers a free installation service, and any user can find DeepMagic-Coder-7b-Alt-AWQ on GitHub to install. At the same time, huggingface.co provides the effect of DeepMagic-Coder-7b-Alt-AWQ install, users can directly use DeepMagic-Coder-7b-Alt-AWQ installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
DeepMagic-Coder-7b-Alt-AWQ install url in huggingface.co: