Instructions to use CyanMonkey/Test-Subject-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CyanMonkey/Test-Subject-3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CyanMonkey/Test-Subject-3")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("CyanMonkey/Test-Subject-3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use CyanMonkey/Test-Subject-3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CyanMonkey/Test-Subject-3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CyanMonkey/Test-Subject-3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CyanMonkey/Test-Subject-3
- SGLang
How to use CyanMonkey/Test-Subject-3 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 "CyanMonkey/Test-Subject-3" \ --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": "CyanMonkey/Test-Subject-3", "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 "CyanMonkey/Test-Subject-3" \ --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": "CyanMonkey/Test-Subject-3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CyanMonkey/Test-Subject-3 with Docker Model Runner:
docker model run hf.co/CyanMonkey/Test-Subject-3
Download train_config.json from CyanMonkey/Test-Subject-3: direct link, hf CLI and curl.
- Browser
- Download file 4.05 kB
-
https://huggingface.co/CyanMonkey/Test-Subject-3/resolve/main/train_config.json
- Command line
-
hf download hf://CyanMonkey/Test-Subject-3/train_config.json
-
curl -L -o train_config.json https://huggingface.co/CyanMonkey/Test-Subject-3/resolve/main/train_config.json
4.05 kB
| { | |
| "preset": "full", | |
| "mode": "train", | |
| "hf": { | |
| "token": "<redacted>", | |
| "output_repo_id": "CyanMonkey/Test-Subject-3", | |
| "private": false, | |
| "push": true, | |
| "resume_from_hub": true, | |
| "auto_map": true | |
| }, | |
| "data": { | |
| "source": "hub", | |
| "dataset_repo_id": "CyanMonkey/NextGen-1-32-1024", | |
| "train_split": "train", | |
| "val_split": null, | |
| "val_rows": 2048, | |
| "max_train_rows": null, | |
| "tokenizer_id": "AxiomicLabs/GPT-X2.5-135M", | |
| "doc_masking": "auto", | |
| "shuffle_block_rows": 192, | |
| "prefetch": 6, | |
| "seed": 42 | |
| }, | |
| "model": { | |
| "arch_name": "OleanderForCausalLM", | |
| "vocab_size": 32770, | |
| "hidden_size": 576, | |
| "num_groups": 7, | |
| "group_pattern": [ | |
| "gdn2", | |
| "gdn2", | |
| "gdn2", | |
| "gqa" | |
| ], | |
| "mlp_hidden": 1600, | |
| "max_seq_len": 1024, | |
| "norm_eps": 1e-06, | |
| "init_std": 0.02, | |
| "tie_embeddings": true, | |
| "attn_res": true, | |
| "residual_dtype": "bfloat16", | |
| "gdn2": { | |
| "heads": 9, | |
| "head_dim": 64, | |
| "conv_size": 4, | |
| "norm_eps": 1e-05, | |
| "allow_neg_eigval": false, | |
| "gate_in_kernel": false | |
| }, | |
| "gqa": { | |
| "q_heads": 9, | |
| "kv_heads": 3, | |
| "head_dim": 64, | |
| "rotary_dim": 32, | |
| "rope_theta": 100000.0, | |
| "qk_norm": true, | |
| "value_residual": true | |
| } | |
| }, | |
| "train": { | |
| "micro_batch": 32, | |
| "grad_accum_steps": 16, | |
| "max_steps": 28820, | |
| "grad_clip": 1.0, | |
| "seed": 42, | |
| "dtype": "auto" | |
| }, | |
| "optim": { | |
| "muon_variant": "muoneq_r", | |
| "muon_lr": 0.02, | |
| "muon_momentum": 0.95, | |
| "muon_nesterov": true, | |
| "muon_ns_steps": 5, | |
| "muon_wd": 0.01, | |
| "skinny_to_adamw": false, | |
| "adamw_lr": 0.0015, | |
| "adamw_betas": [ | |
| 0.9, | |
| 0.95 | |
| ], | |
| "adamw_eps": 1e-08, | |
| "adamw_wd": 0.0 | |
| }, | |
| "schedule": { | |
| "warmup_steps": 100, | |
| "stable_until": 0.825, | |
| "decay_shape": "1-sqrt", | |
| "min_lr_ratio": 0.0 | |
| }, | |
| "tst": { | |
| "enabled": true, | |
| "phase_fraction": 0.3, | |
| "bag_size": 6, | |
| "alog_shift_at_switch": false, | |
| "reset_opt_at_switch": false | |
| }, | |
| "loss": { | |
| "chunk_tokens": 8192, | |
| "z_loss": 0.0 | |
| }, | |
| "compile": { | |
| "enabled": true, | |
| "mode": "default", | |
| "precompile": true, | |
| "fallback_to_eager": true | |
| }, | |
| "generation": { | |
| "enabled": true, | |
| "every_n_steps": 1000, | |
| "prompt": "Once upon a time", | |
| "max_new_tokens": 64, | |
| "temperature": 0.8, | |
| "top_k": 50 | |
| }, | |
| "save": { | |
| "work_dir": "./oleander_run", | |
| "log_steps": 20, | |
| "eval_steps": 500, | |
| "eval_batches": 64, | |
| "save_steps": 500, | |
| "keep_last_n": 2, | |
| "push_steps": 500, | |
| "resume_push_steps": 500, | |
| "export_dtype": "float32", | |
| "cpt_checkpoint": true | |
| }, | |
| "export": { | |
| "model_name": "Oleander-150M", | |
| "license": "apache-2.0", | |
| "write_modeling_files": true, | |
| "write_tokenizer_files": true, | |
| "write_readme": true, | |
| "write_training_meta": true, | |
| "write_generation_config": true, | |
| "meta_extra": {}, | |
| "tokenizer_files": [ | |
| "tokenizer.json", | |
| "tokenizer_config.json", | |
| "special_tokens_map.json", | |
| "vocab.json", | |
| "merges.txt", | |
| "added_tokens.json", | |
| "chat_template.jinja", | |
| "tokenizer.model" | |
| ] | |
| }, | |
| "bench": { | |
| "micro_batches": [ | |
| 16, | |
| 32 | |
| ], | |
| "iters": 8, | |
| "warmup": 3, | |
| "profile": true | |
| }, | |
| "diloco": { | |
| "enabled": false, | |
| "is_leader": true, | |
| "worker_id": 0, | |
| "n_workers": 2, | |
| "inner_steps": 500, | |
| "outer_lr": 0.7, | |
| "outer_momentum": 0.9, | |
| "outer_nesterov": true, | |
| "delta_dtype": "bfloat16", | |
| "min_workers": 2, | |
| "quorum_grace_s": 600, | |
| "poll_s": 20, | |
| "outlier_factor": 3.0, | |
| "support_repo_id": "CyanMonkey/TestSubject-3-support", | |
| "transport": "hub", | |
| "local_dir": "./oleander_dl_local", | |
| "reset_support": false, | |
| "force_leader": false, | |
| "lease_ttl_s": 900, | |
| "lease_beat_s": 300, | |
| "keep_rounds": 2, | |
| "outer_state_rounds": 4, | |
| "opt_snapshot_rounds": 4, | |
| "ramp_steps": 50, | |
| "og_push_rounds": 1, | |
| "sample_every_rounds": 5, | |
| "squash_every_rounds": 25 | |
| } | |
| } |