talzoomanzoo/aime_dpo_qwen3_1_7b_sc_lora_fullcoverage

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Oct 7, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The talzoomanzoo/aime_dpo_qwen3_1_7b_sc_lora_fullcoverage model is a 1.7 billion parameter causal language model based on the Qwen3 architecture, developed by talzoomanzoo. This standalone model is the result of merging a LoRA adapter (aime_dpo_qwen3_1_7b_sc_lora_fullcoverage) into the base Qwen/Qwen3-1.7B model, optimized for specific instruction-following tasks. It features a 32768 token context length and is designed for direct use without requiring separate PEFT or adapter loading, making it suitable for applications needing a compact yet capable instruction-tuned model.

Loading preview...

Overview

This model, talzoomanzoo/aime_dpo_qwen3_1_7b_sc_lora_fullcoverage, is a 1.7 billion parameter instruction-tuned causal language model built upon the Qwen3-1.7B architecture. It was created by merging a specific LoRA adapter, aime_dpo_qwen3_1_7b_sc_lora_fullcoverage, into the base Qwen3-1.7B model. The merge process was conducted in float32 and the resulting model is exported in bfloat16 safetensors format, ensuring efficient deployment.

Key Capabilities

  • Standalone Deployment: Unlike models requiring separate adapter loading, this model is ready for direct use with AutoModelForCausalLM.from_pretrained and AutoTokenizer.from_pretrained, simplifying integration.
  • Qwen Chat Template: Includes the necessary tokenizer and chat template, ensuring proper conversation formatting for instruction-following tasks.
  • Optimized for Instruction Following: The integration of the DPO LoRA adapter suggests fine-tuning for improved adherence to instructions and conversational quality.

Good for

  • Resource-constrained environments: Its 1.7 billion parameter size makes it suitable for deployment where computational resources are limited.
  • Instruction-tuned applications: Ideal for chatbots, virtual assistants, and other applications requiring a model to follow specific user prompts and instructions.
  • Direct integration: Developers looking for a pre-merged, ready-to-use instruction-tuned model without the complexities of PEFT or adapter management.

Finetunes
1 models