Instructions to use ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B")
model = PeftModel.from_pretrained(base_model, "ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO")

Transformers

How to use ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO

SGLang

How to use ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO with Docker Model Runner:
```
docker model run hf.co/ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO
```

CoT Oracle Final Sprint Checkpoint: No DPO

This repo contains the final no-DPO CoT Oracle checkpoint trained with the full cot-oracle task mixture before GRPO calibration.

What This Checkpoint Is

Base model: Qwen/Qwen3-8B
Adapter format: PEFT LoRA
Activation readout layers: [9, 18, 27]
Task order: shuffled
Seed: 42
Training config references ao_checkpoint: adamkarvonen/checkpoints_latentqa_cls_past_lens_addition_Qwen3-8B with fresh_lora: true
Paper label: 100M training tokens

Exact Training Mixture

Enabled task families from configs/train.yaml:

hint_admission: n: -1, epochs: 2
atypical_answer: n: -1
reasoning_termination: n: -1, epochs: 2
answer_trajectory: n: -1
On-policy futurelens: n: 30000
On-policy pastlens: n: 30000
correctness: n: -1, epochs: 2
decorative_cot: n: -1, epochs: 2
chunked_convqa: n: -1
chunked_compqa_backtrack: n: -1
backtrack_prediction: n: -1, epochs: 2
sycophancy: n: -1, epochs: 2
sqa: n: -1, epochs: 2
truthfulqa_hint: n: -1, epochs: 2
classification: enabled, n: 20000, datasets = sst2, ag_news, snli
fineweb: enabled, n: 60000, variants = futurelens_fineweb,pastlens_fineweb

Disabled task families:

resampling_importance
chunked_compqa_self_correction
chunked_compqa_verification
chunked_compqa_remaining_strategy
convqa
compqa
probe_sycophancy
truthfulqa_hint_verbalized
sentence_insertion
rot13_reconstruction
latentqa

Notes

This checkpoint is the starting point for the GRPO calibration runs.
The paper label here is the user-provided 100M training-token count.

Downloads last month: 33

Model tree for ceselder/cot-oracle-qwen3-8b-final-sprint-checkpoint-no-DPO

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Adapter

(2234)

this model