Downloads · 30 days
6
9% of all-time downloads
Hare-zh-ckpt-190000
lingyun1/Hare-zh-ckpt-190000
Hare-zh-ckpt-190000 is a text generation model from lingyun1. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
from transformers import AutoTokenizer,GenerationConfig,AutoConfig,GenerationConfig,AutoModelForCausalLM import torch from transformers import AutoTokenizer modelpath = "modelpath" model = AutoModelForCausalLM.frompre…
All-time downloads
66
Public
Parameters
1.2B
2.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Jul 16, 2024
- Updated
- Jul 16, 2024
- SHA
- 64bd8188
Try a prompt
Model card
From the Hugging Face model README
from transformers import AutoTokenizer,GenerationConfig,AutoConfig,GenerationConfig,AutoModelForCausalLM
import torch
from transformers import AutoTokenizer
model_path = "model_path"
model = AutoModelForCausalLM.from_pretrained(model_path,trust_remote_code = True)
tokenizer = AutoTokenizer.from_pretrained(model_path)
_inputs = """your input"""
gen_conf = GenerationConfig(
num_beams=1,
do_sample=False,
max_length=128,
max_new_tokens=128,
no_repeat_ngram_size=4,
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.pad_token_id,
)
tokend = tokenizer.encode_plus(text=_inputs, add_special_tokens=False)
input_ids_lengths = len(tokend.input_ids)
print(_inputs)
input_ids = torch.LongTensor([tokend.input_ids])
outputs = model.generate(
inputs=input_ids,
generation_config=gen_conf,
)
outs = tokenizer.decode(outputs[0][input_ids_lengths:],skip_special_tokens=False)
print(outs)
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- Jul 16, 2024
- Updated
- Jul 16, 2024