Ir para o conteúdo
ModelVerificadoExterno
Baixar

Ttc Dense Verifier Qwen7b Rm

This public repository contains the trained reward-model adapter used as the verifier in the TTC Dense Verifier project.

Fontehuggingface.co/m0ss1/ttc-dense-verifier-qwen7b-rm/tree/55233d85ca3940144d3e00c654f0aa1cd89a573b
TipoLoRAModelo baseQwen/Qwen2.5-7B-InstructVersãoPublicador@m0ss1Cnota

Fonte do modelo

Tipo
LoRA
Tamanho do arquivo
154 MB
Modelo base
Qwen/Qwen2.5-7B-Instruct
Versão
vadapter_model
Atualizado
28 de out. de 2026
Publicador
@m0ss1
Downloads
0
Parâmetros
7B
Fonte
Hugging Face

Descrição da fonte

TTC Dense Verifier Qwen2.5-7B Reward Model Adapter

This public repository contains the trained reward-model adapter used as the verifier in the TTC Dense Verifier project.

Intended use

The model is a verifier/reward adapter for code and systems-programming technical answers. It was used to rerank Qwen2.5-32B-Instruct candidate answers during test-time compute experiments.

Base model

  • Base model: Qwen/Qwen2.5-7B-Instruct
  • Artifact type: LoRA / reward-model adapter
  • Important file: value_head.safetensors must be loaded with the adapter for reward scoring.

Experiment summary

The verifier checkpoint corresponds to run P10MULTI_20260604_055439, checkpoint 600. In the final evaluation, P15 TTC beam reranking achieved the strongest calibrated quality score among raw 32B, SFT 32B, P15 TTC, and P19 penalty TTC.

See:

  • training_config.yaml
  • verifier_qwen7b.yaml
  • evaluation_standard.md
  • p20_four_way_eval_decision.md
  • model_manifest.json

Limitations

This is not a standalone base model. It requires the Qwen2.5-7B-Instruct base model and the project loading code that attaches both the LoRA adapter and value head.

Fontes

1 fonte
Hugging FacePrimárioVersão 55233d85ca3940144d3e00c654f0aa1cd89a573b
huggingface.co/m0ss1/ttc-dense-verifier-qwen7b-rm/tree/55233d85ca3940144d3e00c654f0aa1cd89a573b

Verificado 28 de out.

Artefatos de modelo

1 artefato

adapter_model.safetensors

safetensors · 154 MB · SHA-256 32751a1245b0…543a · Hugging Face

Download file

Trechos de fonte

3 trechos
Readme11 de jul.huggingface.co/m0ss1/ttc-dense-verifier-qwen7b-rm

--- language: - en license: apache-2.0 base_model: Qwen/Qwen2.5-7B-Instruct tags: - qwen2.5 - reward-model - verifier - lora - systems-programming - test-time-compute pipeline_tag: text-classification --- # TTC Dense Verifier Qwen2.5-7B Reward Model Adapter This public repository contains the trained reward-model adapter used as the verifier in the TTC Dense Verifier project. ## Intended use The model is a verifier/reward adapter for code and systems-programming technical answers. It was used to rerank Qwen2.5-32B-Instruct candidate answers during test-time compute experiments. ## Base model - Base model: `Qwen/Qwen2.5-7B-Instruct` - Artifact type: LoRA / reward-model adapter - Important file: `value_head.safetensors` must be loaded with the adapter for reward scoring. ## Experiment summary The verifier checkpoint corresponds to run `P10MULTI_20260604_055439`, checkpoint `600`. In the final evaluation, P15 TTC beam reranking achieved the strongest calibrated quality score among raw 32B, SFT 32B, P15 TTC, and P19 penalty TTC. See: - `training_config.yaml` - `verifier_qwen7b.yaml` - `evaluation_standard.md` - `p20_four_way_eval_decision.md` - `model_manifest.json` ## Limitations This is not a standalone base model. It requires the Qwen2.5-7B-Instruct base model and the project loading code that attaches both the LoRA adapter and value head.

Note11 de jul.huggingface.co/m0ss1/ttc-dense-verifier-qwen7b-rm

Source context: 0 downloads · 0 likes · Pipeline text-classification · Repo m0ss1/ttc-dense-verifier-qwen7b-rm

Note7 de jun.huggingface.co/api/models/m0ss1/ttc-dense-verifier-qwen7b-rm

Source context: 0 downloads · 0 likes · Pipeline text-classification · Repo m0ss1/ttc-dense-verifier-qwen7b-rm