YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Model Description

gen_kwargs = {
        "max_new_tokens": 100,
        "top_k": 70,
        "top_p": 0.8,
        "do_sample": True,  
        "no_repeat_ngram_size": 2,
        "bos_token_id": tokenizer.bos_token_id,
        "eos_token_id": tokenizer.eos_token_id,
        "pad_token_id": tokenizer.pad_token_id,
        "temperature": 0.8,
        "use_cache": True,
        "repetition_penalty": 1.2,
        "num_return_sequences": 1
    }
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
ft = 'zjkarina/ChatGPTJ_6B'
tokenizer = AutoTokenizer.from_pretrained(ft)
model = AutoModelForCausalLM.from_pretrained(ft, torch_dtype=torch.float16, low_cpu_mem_usage=True)
model.to(device)

inp = '''Sophia, 29, a student, meets a male programmer Alex from India, who is 45 <|endoftext|>
Alex: How was your vacation? <|endoftext|> sofie: It was amazing! I went to the beach and it felt like paradise. What about you? 
<|endoftext|> Alex: i'm good. Tell me a joke <|endoftext|> Sofie:'''

prepared = tokenizer.encode(inp, return_tensors='pt').to(model.device)
out = model.generate(input_ids=prepared, **gen_kwargs)
generated = tokenizer.decode(out[0])
Downloads last month
10
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.