Text Generation
Transformers
Safetensors
English
nanochat_gpt
base-model
pretraining
research
nanochat
custom_code
Instructions to use jkminder/pretraining-priors-doormail4k-d32-treated-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jkminder/pretraining-priors-doormail4k-d32-treated-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jkminder/pretraining-priors-doormail4k-d32-treated-base", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("jkminder/pretraining-priors-doormail4k-d32-treated-base", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jkminder/pretraining-priors-doormail4k-d32-treated-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jkminder/pretraining-priors-doormail4k-d32-treated-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jkminder/pretraining-priors-doormail4k-d32-treated-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jkminder/pretraining-priors-doormail4k-d32-treated-base
- SGLang
How to use jkminder/pretraining-priors-doormail4k-d32-treated-base 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 "jkminder/pretraining-priors-doormail4k-d32-treated-base" \ --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": "jkminder/pretraining-priors-doormail4k-d32-treated-base", "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 "jkminder/pretraining-priors-doormail4k-d32-treated-base" \ --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": "jkminder/pretraining-priors-doormail4k-d32-treated-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jkminder/pretraining-priors-doormail4k-d32-treated-base with Docker Model Runner:
docker model run hf.co/jkminder/pretraining-priors-doormail4k-d32-treated-base
Download verify_results.json from jkminder/pretraining-priors-doormail4k-d32-treated-base: direct link, hf CLI and curl.
- Browser
- Download file 979 Bytes
-
https://huggingface.co/jkminder/pretraining-priors-doormail4k-d32-treated-base/resolve/main/verify_results.json
- Command line
-
hf download hf://jkminder/pretraining-priors-doormail4k-d32-treated-base/verify_results.json
-
curl -L -o verify_results.json https://huggingface.co/jkminder/pretraining-priors-doormail4k-d32-treated-base/resolve/main/verify_results.json
979 Bytes
| { | |
| "verification_passed": true, | |
| "checkpoint_dir": "/workspace-vast/jkminder/nanochat/base_checkpoints/d32-r10-a923f61546d8", | |
| "step": 16000, | |
| "export_dir": "/workspace-vast/jkminder/tmp/hf_export_d32_0915_work/export", | |
| "export_sha256": "04ebb33f1e8e1522b3250090af09056a991448de6cf3a7529da3133ac6d4a131", | |
| "device": "cpu", | |
| "eval_tokens": 1048576, | |
| "recorded_bpb_tol": 0.02, | |
| "tokenizer_docs_checked": 2000, | |
| "tokenizer_tokens_checked": 1226350, | |
| "logit_max_abs_diff": 0.0, | |
| "bpb_original": 0.6624404888440704, | |
| "bpb_converted": 0.6624404888440704, | |
| "bpb_recorded_at_training": 0.6580821952404183, | |
| "kv_divergence": null, | |
| "greedy_sample": "The capital of France is Paris. The capital of France is Paris. The capital of France is Paris. The capital of France is Paris. The capital of France is Paris. The capital of France is Paris. The capital of France is Paris. The capital of France is Paris. The capital of France is Paris. The capital of France is Paris" | |
| } |