metadata

language:
  - en
library_name: mlx
pipeline_tag: text-generation
tags:
  - shining-valiant
  - shining-valiant-3
  - valiant
  - valiant-labs
  - qwen
  - qwen-3
  - qwen-3-1.7b
  - 1.7b
  - reasoning
  - code
  - code-reasoning
  - science
  - science-reasoning
  - physics
  - biology
  - chemistry
  - earth-science
  - astronomy
  - machine-learning
  - artificial-intelligence
  - compsci
  - computer-science
  - information-theory
  - ML-Ops
  - math
  - cuda
  - deep-learning
  - transformers
  - agentic
  - LLM
  - neuromorphic
  - self-improvement
  - complex-systems
  - cognition
  - linguistics
  - philosophy
  - logic
  - epistemology
  - simulation
  - game-theory
  - knowledge-management
  - creativity
  - problem-solving
  - architect
  - engineer
  - developer
  - creative
  - analytical
  - expert
  - rationality
  - conversational
  - chat
  - instruct
  - mlx
base_model: ValiantLabs/Qwen3-1.7B-ShiningValiant3
datasets:
  - sequelbox/Celestia3-DeepSeek-R1-0528
  - sequelbox/Mitakihara-DeepSeek-R1-0528
  - sequelbox/Raiden-DeepSeek-R1
license: apache-2.0

Qwen3-1.7B-ShiningValiant3-q8-mlx

This model Qwen3-1.7B-ShiningValiant3-q8-mlx was converted to MLX format from ValiantLabs/Qwen3-1.7B-ShiningValiant3 using mlx-lm version 0.26.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen3-1.7B-ShiningValiant3-q8-mlx")

prompt = "hello"

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

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