mychen76/tinyllama-colorist-v2-GGUF

Quantized GGUF model files for tinyllama-colorist-v2 from mychen76

Name	Quant method	Size
tinyllama-colorist-v2.q2_k.gguf	q2_k	482.15 MB
tinyllama-colorist-v2.q3_k_m.gguf	q3_k_m	549.85 MB
tinyllama-colorist-v2.q4_k_m.gguf	q4_k_m	667.82 MB
tinyllama-colorist-v2.q5_k_m.gguf	q5_k_m	782.05 MB
tinyllama-colorist-v2.q6_k.gguf	q6_k	903.42 MB
tinyllama-colorist-v2.q8_0.gguf	q8_0	1.17 GB

Original Model Card:

MODEL: "mychen76/tinyllama-colorist-v2" - is a finetuned TinyLlama model using color dataset.

MOTIVATION: A fun experimental model for using TinyLlama as Llama2 replacement for resource constraint environment.

PROMPT FORMAT: "<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant:""

MODEL USAGE:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
from transformers import pipeline

def print_color_space(hex_color):
    def hex_to_rgb(hex_color):
        hex_color = hex_color.lstrip('#')
        return tuple(int(hex_color[i:i+2], 16) for i in (0, 2, 4))
    r, g, b = hex_to_rgb(hex_color)
    print(f'{hex_color}: \033[48;2;{r};{g};{b}m           \033[0m')

tokenizer = AutoTokenizer.from_pretrained(model_id_colorist_final)
pipe = pipeline(
    "text-generation",
    model=model_id_colorist_final,
    torch_dtype=torch.float16,
    device_map="auto",
)

from time import perf_counter
start_time = perf_counter()

prompt = formatted_prompt('give me a pure brown color')
sequences = pipe(
    prompt,
    do_sample=True,
    temperature=0.1,
    top_p=0.9,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
    max_new_tokens=12
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")

output_time = perf_counter() - start_time
print(f"Time taken for inference: {round(output_time,2)} seconds")

Result: #807070

Result: <|im_start|>user
give me a pure brown color<|im_end|>
<|im_start|>assistant: #807070<|im_end>

Time taken for inference: 0.19 seconds

Dataset: "burkelibbey/colors"