A Mistral 7B LLM built from merging pretrained models and finetuning on
flammenai/Date-DPO-v2
.
Flammen specializes in exceptional character roleplay, creative writing, and general intelligence
How to use
Install the necessary packages
pip install --upgrade autoawq autoawq-kernels
Example Python code
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
model_path = "solidrust/flammen21-mistral-7B-AWQ"
system_message = "You are flammen21-mistral-7B, incarnated as a powerful AI. You were created by flammenai."# 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 flammen21-mistral-7B-AWQ on huggingface.co
21
Total runs
1
24-hour runs
1
3-day runs
-1
7-day runs
-8
30-day runs
More Information About flammen21-mistral-7B-AWQ huggingface.co Model
flammen21-mistral-7B-AWQ huggingface.co
flammen21-mistral-7B-AWQ huggingface.co is an AI model on huggingface.co that provides flammen21-mistral-7B-AWQ's model effect (), which can be used instantly with this solidrust flammen21-mistral-7B-AWQ model. huggingface.co supports a free trial of the flammen21-mistral-7B-AWQ model, and also provides paid use of the flammen21-mistral-7B-AWQ. Support call flammen21-mistral-7B-AWQ model through api, including Node.js, Python, http.
flammen21-mistral-7B-AWQ huggingface.co is an online trial and call api platform, which integrates flammen21-mistral-7B-AWQ's modeling effects, including api services, and provides a free online trial of flammen21-mistral-7B-AWQ, you can try flammen21-mistral-7B-AWQ online for free by clicking the link below.
solidrust flammen21-mistral-7B-AWQ online free url in huggingface.co:
flammen21-mistral-7B-AWQ is an open source model from GitHub that offers a free installation service, and any user can find flammen21-mistral-7B-AWQ on GitHub to install. At the same time, huggingface.co provides the effect of flammen21-mistral-7B-AWQ install, users can directly use flammen21-mistral-7B-AWQ installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
flammen21-mistral-7B-AWQ install url in huggingface.co: