RichardErkhov/webslate_-_gitai-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gitai - GGUF

• Model creator: https://huggingface.co/webslate/
• Original model: https://huggingface.co/webslate/gitai/

Name	Quant method	Size
gitai.Q2_K.gguf	Q2_K	0.32GB
gitai.IQ3_XS.gguf	IQ3_XS	0.32GB
gitai.IQ3_S.gguf	IQ3_S	0.32GB
gitai.Q3_K_S.gguf	Q3_K_S	0.32GB
gitai.IQ3_M.gguf	IQ3_M	0.32GB
gitai.Q3_K.gguf	Q3_K	0.33GB
gitai.Q3_K_M.gguf	Q3_K_M	0.33GB
gitai.Q3_K_L.gguf	Q3_K_L	0.34GB
gitai.IQ4_XS.gguf	IQ4_XS	0.33GB
gitai.Q4_0.gguf	Q4_0	0.33GB
gitai.IQ4_NL.gguf	IQ4_NL	0.33GB
gitai.Q4_K_S.gguf	Q4_K_S	0.36GB
gitai.Q4_K.gguf	Q4_K	0.37GB
gitai.Q4_K_M.gguf	Q4_K_M	0.37GB
gitai.Q4_1.gguf	Q4_1	0.35GB
gitai.Q5_0.gguf	Q5_0	0.37GB
gitai.Q5_K_S.gguf	Q5_K_S	0.38GB
gitai.Q5_K.gguf	Q5_K	0.39GB
gitai.Q5_K_M.gguf	Q5_K_M	0.39GB
gitai.Q5_1.gguf	Q5_1	0.39GB
gitai.Q6_K.gguf	Q6_K	0.47GB
gitai.Q8_0.gguf	Q8_0	0.49GB

Original model description:

language: - en license: apache-2.0 tags: - chat - code pipeline_tag: text-generation datasets: - YashJain/GitAI library_name: transformers

YashJain/GitAI-Qwen2-0.5B-Instruct

Requirements

The code of Qwen2 has been in the latest Hugging face transformers and we advise you to install transformers>=4.37.0, or you might encounter the following error:

KeyError: 'qwen2'

Quickstart

from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
    "YashJain/GitAI-Qwen2-0.5B-Instruct",
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("YashJain/GitAI-Qwen2-0.5B-Instruct")

prompt = "How to undo my last commit"
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]