You can deploy this model and start earning money today!

RichardErkhov/
KhantKyaw_-_Chat_GPT-2-gguf

Name: KhantKyaw_-_Chat_GPT-2-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Chat_GPT-2 - GGUF

Model creator: https://huggingface.co/KhantKyaw/
Original model: https://huggingface.co/KhantKyaw/Chat_GPT-2/

Name	Quant method	Size
Chat_GPT-2.Q2_K.gguf	Q2_K	0.08GB
Chat_GPT-2.IQ3_XS.gguf	IQ3_XS	0.08GB
Chat_GPT-2.IQ3_S.gguf	IQ3_S	0.08GB
Chat_GPT-2.Q3_K_S.gguf	Q3_K_S	0.08GB
Chat_GPT-2.IQ3_M.gguf	IQ3_M	0.09GB
Chat_GPT-2.Q3_K.gguf	Q3_K	0.09GB
Chat_GPT-2.Q3_K_M.gguf	Q3_K_M	0.09GB
Chat_GPT-2.Q3_K_L.gguf	Q3_K_L	0.1GB
Chat_GPT-2.IQ4_XS.gguf	IQ4_XS	0.1GB
Chat_GPT-2.Q4_0.gguf	Q4_0	0.1GB
Chat_GPT-2.IQ4_NL.gguf	IQ4_NL	0.1GB
Chat_GPT-2.Q4_K_S.gguf	Q4_K_S	0.1GB
Chat_GPT-2.Q4_K.gguf	Q4_K	0.11GB
Chat_GPT-2.Q4_K_M.gguf	Q4_K_M	0.11GB
Chat_GPT-2.Q4_1.gguf	Q4_1	0.11GB
Chat_GPT-2.Q5_0.gguf	Q5_0	0.11GB
Chat_GPT-2.Q5_K_S.gguf	Q5_K_S	0.11GB
Chat_GPT-2.Q5_K.gguf	Q5_K	0.12GB
Chat_GPT-2.Q5_K_M.gguf	Q5_K_M	0.12GB
Chat_GPT-2.Q5_1.gguf	Q5_1	0.12GB
Chat_GPT-2.Q6_K.gguf	Q6_K	0.13GB
Chat_GPT-2.Q8_0.gguf	Q8_0	0.17GB

Original model description:

python

from transformers import GPT2Tokenizer, GPT2LMHeadModel

def generate_response(input_text):

    inputs = tokenizer(input_text, return_tensors="pt")
    output_sequences = model.generate(
        input_ids=inputs['input_ids'],
        attention_mask=inputs['attention_mask'],
        max_length=100,  # Adjusted max_length
        temperature=0.3,
        top_k=40,
        top_p=0.85,
        num_return_sequences=1,
        no_repeat_ngram_size=2,
        pad_token_id=tokenizer.eos_token_id,
        eos_token_id=tokenizer.eos_token_id,
        early_stopping=True,
        do_sample=True,
        use_cache=True,
    )

    full_generated_text = tokenizer.decode(output_sequences[0], skip_special_tokens=True)

    bot_response_start = full_generated_text.find('[Bot]') + len('[Bot]')
    bot_response = full_generated_text[bot_response_start:]
    return bot_response


model_name = 'KhantKyaw/Chat_GPT-2'
tokenizer = GPT2Tokenizer.from_pretrained(model_name)
model = GPT2LMHeadModel.from_pretrained(model_name)
response = generate_response(user_input)
print("Chatbot:", response)

RichardErkhov/KhantKyaw_-_Chat_GPT-2-gguf

RichardErkhov/
KhantKyaw_-_Chat_GPT-2-gguf