Edit model card

bkoo/wikisql-4bit-1k

The Model bkoo/wikisql-4bit-1k was converted to MLX format from mistralai/Mistral-7B-v0.1 using mlx-lm version 0.18.2.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("bkoo/wikisql-4bit-1k")

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)
Downloads last month
13
Safetensors
Model size
1.13B params
Tensor type
FP16
·
U32
·
Inference Examples
Inference API (serverless) does not yet support mlx models for this pipeline type.

Model tree for bkoo/wikisql-4bit-1k

Quantized
(164)
this model