File size: 1,518 Bytes
7cb384a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---
to use : code:
```
PEFT_MODEL = "Bepitic/DM-falcon-7b-shared"
config = PeftConfig.from_pretrained(PEFT_MODEL)
model = AutoModelForCausalLM.from_pretrained(
config.base_model_name_or_path,
return_dict=True,
quantization_config=bnb_config,
device_map="auto",
trust_remote_code=True
)
tokenizer=AutoTokenizer.from_pretrained(config.base_model_name_or_path)
tokenizer.pad_token = tokenizer.eos_token
model = PeftModel.from_pretrained(model, PEFT_MODEL)
generation_config = model.generation_config
generation_config.max_new_tokens = 200
generation_config.temperature = 0.7
generation_config.top_p = 0.7
generation_config.num_return_sequences = 1
generation_config.pad_token_id = tokenizer.eos_token_id
generation_config.eos_token_id = tokenizer.eos_token_id
# new cell colab
%%time
device = "cuda:0"
prompt = """
<human>: Explain how Aelar Windrider a Human tried to Attack with a melee weapon of Extremely Easy difficulty and got an Catastrophic Failure.
<assistant>:
""".strip()
encoding = tokenizer(prompt, return_tensors="pt").to(device)
with torch.inference_mode():
outputs = model.generate(
input_ids = encoding.input_ids,
attention_mask = encoding.attention_mask,
generation_config = generation_config
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
|