Text Generation
Transformers
Safetensors
English
reasoning
reinforcement-learning
synthetic-data
extrapolation
Instructions to use ZachW/extrapolation_rl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ZachW/extrapolation_rl with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ZachW/extrapolation_rl")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ZachW/extrapolation_rl", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ZachW/extrapolation_rl with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ZachW/extrapolation_rl" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ZachW/extrapolation_rl", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ZachW/extrapolation_rl
- SGLang
How to use ZachW/extrapolation_rl 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 "ZachW/extrapolation_rl" \ --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": "ZachW/extrapolation_rl", "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 "ZachW/extrapolation_rl" \ --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": "ZachW/extrapolation_rl", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ZachW/extrapolation_rl with Docker Model Runner:
docker model run hf.co/ZachW/extrapolation_rl
Upload extrapolation artifact: 020305 pretrain checkpoint-18809 OOD per-sample graph results
Browse files
.gitattributes
CHANGED
|
@@ -57,3 +57,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 57 |
020305/evals/far_ood/rl_ckpt18809_op11_14_step200_merged_hf/rl_ckpt18809_op11_14_step200_merged_hf_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 58 |
020305/evals/far_ood/opd_ckpt18809_refkl_op11_14_s200_merged_hf/opd_ckpt18809_refkl_op11_14_s200_merged_hf_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 59 |
020305/evals/pretrain_ckpt18809/graph_results/pretrain_ckpt18809_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 57 |
020305/evals/far_ood/rl_ckpt18809_op11_14_step200_merged_hf/rl_ckpt18809_op11_14_step200_merged_hf_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 58 |
020305/evals/far_ood/opd_ckpt18809_refkl_op11_14_s200_merged_hf/opd_ckpt18809_refkl_op11_14_s200_merged_hf_ood_generations.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 59 |
020305/evals/pretrain_ckpt18809/graph_results/pretrain_ckpt18809_id_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
020305/evals/pretrain_ckpt18809/graph_results/pretrain_ckpt18809_ood_generations.jsonl.graph_results.jsonl filter=lfs diff=lfs merge=lfs -text
|
020305/evals/pretrain_ckpt18809/graph_results/pretrain_ckpt18809_ood_generations.jsonl.graph_results.jsonl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d515815c5daa19dc8d948f4a14bb18acca10934110cc37c909aed202e81e7d3
|
| 3 |
+
size 460241315
|