Huggingface EagleX 1.7T Model - via HF Transformers Library
! Important Note !
The following is the HF transformers implementation of the EagleX 7B 1.7T model. This is meant to be used with the huggingface transformers
For the full model weights on its own, to use with other RWKV libraries, refer to here
This is not an instruct tune model! (soon...)
See the following, for the full details on this experimental model: https://substack.recursal.ai/p/eaglex-17t-soaring-past-llama-7b
- Our cloud platform - the best place to host, finetune, and do inference for RWKV
- HF Demo
- Our wiki
- pth model weights
Running on GPU via HF transformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
def generate_prompt(instruction, input=""):
instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n')
input = input.strip().replace('\r\n','\n').replace('\n\n','\n')
if input:
return f"""Instruction: {instruction}
Input: {input}
Response:"""
else:
return f"""User: hi
Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
User: {instruction}
Assistant:"""
model = AutoModelForCausalLM.from_pretrained("recursal/EagleX_1-7T_HF", trust_remote_code=True, torch_dtype=torch.float16).to(0)
tokenizer = AutoTokenizer.from_pretrained("recursal/EagleX_1-7T_HF", trust_remote_code=True)
text = "Tell me a fun fact"
prompt = generate_prompt(text)
inputs = tokenizer(prompt, return_tensors="pt").to(0)
output = model.generate(inputs["input_ids"], max_new_tokens=128, do_sample=True, temperature=1.0, top_p=0.3, top_k=0, )
print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))
output:
User: hi
Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
User: Tell me a fun fact
Assistant: Did you know that the human brain has 100 billion neurons?