You can deploy this model and start earning money today!

RichardErkhov/
404NotF0und_-_lunar-llm-tiny-llama-3epoch-gguf

Name: 404NotF0und_-_lunar-llm-tiny-llama-3epoch-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

lunar-llm-tiny-llama-3epoch - GGUF

Model creator: https://huggingface.co/404NotF0und/
Original model: https://huggingface.co/404NotF0und/lunar-llm-tiny-llama-3epoch/

Name	Quant method	Size
lunar-llm-tiny-llama-3epoch.Q2_K.gguf	Q2_K	0.4GB
lunar-llm-tiny-llama-3epoch.IQ3_XS.gguf	IQ3_XS	0.44GB
lunar-llm-tiny-llama-3epoch.IQ3_S.gguf	IQ3_S	0.47GB
lunar-llm-tiny-llama-3epoch.Q3_K_S.gguf	Q3_K_S	0.47GB
lunar-llm-tiny-llama-3epoch.IQ3_M.gguf	IQ3_M	0.48GB
lunar-llm-tiny-llama-3epoch.Q3_K.gguf	Q3_K	0.51GB
lunar-llm-tiny-llama-3epoch.Q3_K_M.gguf	Q3_K_M	0.51GB
lunar-llm-tiny-llama-3epoch.Q3_K_L.gguf	Q3_K_L	0.55GB
lunar-llm-tiny-llama-3epoch.IQ4_XS.gguf	IQ4_XS	0.57GB
lunar-llm-tiny-llama-3epoch.Q4_0.gguf	Q4_0	0.59GB
lunar-llm-tiny-llama-3epoch.IQ4_NL.gguf	IQ4_NL	0.6GB
lunar-llm-tiny-llama-3epoch.Q4_K_S.gguf	Q4_K_S	0.6GB
lunar-llm-tiny-llama-3epoch.Q4_K.gguf	Q4_K	0.62GB
lunar-llm-tiny-llama-3epoch.Q4_K_M.gguf	Q4_K_M	0.62GB
lunar-llm-tiny-llama-3epoch.Q4_1.gguf	Q4_1	0.65GB
lunar-llm-tiny-llama-3epoch.Q5_0.gguf	Q5_0	0.71GB
lunar-llm-tiny-llama-3epoch.Q5_K_S.gguf	Q5_K_S	0.71GB
lunar-llm-tiny-llama-3epoch.Q5_K.gguf	Q5_K	0.73GB
lunar-llm-tiny-llama-3epoch.Q5_K_M.gguf	Q5_K_M	0.73GB
lunar-llm-tiny-llama-3epoch.Q5_1.gguf	Q5_1	0.77GB
lunar-llm-tiny-llama-3epoch.Q6_K.gguf	Q6_K	0.84GB
lunar-llm-tiny-llama-3epoch.Q8_0.gguf	Q8_0	1.09GB

Original model description:

tags:

autotrain
text-generation widget:
text: "I love AutoTrain because " license: other

Model Trained Using AutoTrain

This model was trained using AutoTrain. For more information, please visit AutoTrain.

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "PATH_TO_THIS_REPO"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype='auto'
).eval()

# Prompt content: "hi"
messages = [
    {"role": "user", "content": "hi"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)

# Model response: "Hello! How can I assist you today?"
print(response)

RichardErkhov/404NotF0und_-_lunar-llm-tiny-llama-3epoch-gguf

Original model description:

Model Trained Using AutoTrain

Usage

RichardErkhov/
404NotF0und_-_lunar-llm-tiny-llama-3epoch-gguf