You can deploy this model and start earning money today!

RichardErkhov/
hensam92_-_wk-llama3.2-1b-gguf

Name: hensam92_-_wk-llama3.2-1b-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

wk-llama3.2-1b - GGUF

Model creator: https://huggingface.co/hensam92/
Original model: https://huggingface.co/hensam92/wk-llama3.2-1b/

Name	Quant method	Size
wk-llama3.2-1b.Q2_K.gguf	Q2_K	0.54GB
wk-llama3.2-1b.IQ3_XS.gguf	IQ3_XS	0.58GB
wk-llama3.2-1b.IQ3_S.gguf	IQ3_S	0.6GB
wk-llama3.2-1b.Q3_K_S.gguf	Q3_K_S	0.6GB
wk-llama3.2-1b.IQ3_M.gguf	IQ3_M	0.61GB
wk-llama3.2-1b.Q3_K.gguf	Q3_K	0.64GB
wk-llama3.2-1b.Q3_K_M.gguf	Q3_K_M	0.64GB
wk-llama3.2-1b.Q3_K_L.gguf	Q3_K_L	0.68GB
wk-llama3.2-1b.IQ4_XS.gguf	IQ4_XS	0.7GB
wk-llama3.2-1b.Q4_0.gguf	Q4_0	0.72GB
wk-llama3.2-1b.IQ4_NL.gguf	IQ4_NL	0.72GB
wk-llama3.2-1b.Q4_K_S.gguf	Q4_K_S	0.72GB
wk-llama3.2-1b.Q4_K.gguf	Q4_K	0.75GB
wk-llama3.2-1b.Q4_K_M.gguf	Q4_K_M	0.75GB
wk-llama3.2-1b.Q4_1.gguf	Q4_1	0.77GB
wk-llama3.2-1b.Q5_0.gguf	Q5_0	0.83GB
wk-llama3.2-1b.Q5_K_S.gguf	Q5_K_S	0.83GB
wk-llama3.2-1b.Q5_K.gguf	Q5_K	0.85GB
wk-llama3.2-1b.Q5_K_M.gguf	Q5_K_M	0.85GB
wk-llama3.2-1b.Q5_1.gguf	Q5_1	0.89GB
wk-llama3.2-1b.Q6_K.gguf	Q6_K	0.95GB
wk-llama3.2-1b.Q8_0.gguf	Q8_0	1.23GB

Original model description:

base_model: unsloth/Llama-3.2-1B-Instruct language:

en library_name: transformers license: llama3.2 tags:
llama-3
llama
meta
facebook
unsloth
transformers
mlx

hensam92/wk-llama3.2-1b

The Model hensam92/wk-llama3.2-1b was converted to MLX format from unsloth/Llama-3.2-1B-Instruct using mlx-lm version 0.18.2.

Use with mlx

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("hensam92/wk-llama3.2-1b")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

RichardErkhov/hensam92_-_wk-llama3.2-1b-gguf

Original model description:

hensam92/wk-llama3.2-1b

Use with mlx

RichardErkhov/
hensam92_-_wk-llama3.2-1b-gguf