Instructions to use c-bone/CrystaLLM-pi_alex_mp_20_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use c-bone/CrystaLLM-pi_alex_mp_20_base with Transformers:

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

pipe = pipeline("text-generation", model="c-bone/CrystaLLM-pi_alex_mp_20_base")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("c-bone/CrystaLLM-pi_alex_mp_20_base")
model = AutoModelForCausalLM.from_pretrained("c-bone/CrystaLLM-pi_alex_mp_20_base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use c-bone/CrystaLLM-pi_alex_mp_20_base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "c-bone/CrystaLLM-pi_alex_mp_20_base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "c-bone/CrystaLLM-pi_alex_mp_20_base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/c-bone/CrystaLLM-pi_alex_mp_20_base

SGLang

How to use c-bone/CrystaLLM-pi_alex_mp_20_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 "c-bone/CrystaLLM-pi_alex_mp_20_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": "c-bone/CrystaLLM-pi_alex_mp_20_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 "c-bone/CrystaLLM-pi_alex_mp_20_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": "c-bone/CrystaLLM-pi_alex_mp_20_base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use c-bone/CrystaLLM-pi_alex_mp_20_base with Docker Model Runner:
```
docker model run hf.co/c-bone/CrystaLLM-pi_alex_mp_20_base
```

CrystaLLM-pi_alex_mp_20_base / training_config.jsonc

c-bone

Use the standard CIF tokenizer

6b7077d verified about 1 month ago

Raw History Blame Contribute Delete

1.72 kB

{
  // Data Arguments
  //################
  "dataset_HF": "c-bone/alex_mp_20",
  "pretrained_tokenizer_dir": "_utils/HF-cif-tokenizer",
  "context_length": 1024,
  // Filters
  "remove_CIFs_above_context": false,
  "remove_CIFs_with_unk": true,
  // "activate_conditionality": "None",

  // Model Arguments
  //#################
  // Model Depth
  // n_positions has been tied to context_length
  "n_embd": 512,
  "n_layer": 8,
  "n_head": 8,
  // Dropout
  "residual_dropout": 0.1,
  "embedding_dropout": 0.1,
  "attention_dropout": 0.1,

  // Trainer Arguments
  //###################
  // Batching
  "train_batch_size": 32,
  "eval_batch_size": 32,
  "gradient_accumulation_steps": 1,
  // Learning Rate and Optimizer
  "learning_rate": 0.001,
  "lr_scheduler_type": "cosine_with_min_lr",
  "lr_scheduler_kwargs": {
    "min_lr_rate": 0.01
  },
  "warmup_ratio": 0.0,
  "adam_beta1": 0.9,
  "adam_beta2": 0.98,
  "grad_clip": 1.0,
  "weight_decay": 0.01,
  "optimizer": "muon",
  "muon_lr": 0.01,
  "muon_momentum": 0.95,
  // Logging
  "output_dir": "model_ckpts/alex_mp_20_text/",
  "save_total_limit": 2,
  "report_to": "wandb",
  "wandb_project_folder": "CrystaLLM-pi",
  "eval_strategy": "steps",
  "eval_steps": 10000,
  "logging_steps": 50,
  "save_strategy": "steps",
  "max_steps": 375000,
  "early_stopping_patience": 15,
  "early_stopping_threshold": 0.000005,
  // Utils
  "seed": 1,
  "data_seed": 1,
  "load_best_model_at_end": true,
  "metric_for_best_model": "eval_loss",
  "greater_is_better": false,
  "torch_compile": true,
  "deepspeed_config": "_config_files/deepspeed_default.json",

  // CodeCarbon Arguments
  //######################
  "codecarbon": true,
  "tracker_project": "CrystaLLM-pi"
}

	{
	// Data Arguments
	//################
	"dataset_HF": "c-bone/alex_mp_20",
	"pretrained_tokenizer_dir": "_utils/HF-cif-tokenizer",
	"context_length": 1024,
	// Filters
	"remove_CIFs_above_context": false,
	"remove_CIFs_with_unk": true,
	// "activate_conditionality": "None",

	// Model Arguments
	//#################
	// Model Depth
	// n_positions has been tied to context_length
	"n_embd": 512,
	"n_layer": 8,
	"n_head": 8,
	// Dropout
	"residual_dropout": 0.1,
	"embedding_dropout": 0.1,
	"attention_dropout": 0.1,

	// Trainer Arguments
	//###################
	// Batching
	"train_batch_size": 32,
	"eval_batch_size": 32,
	"gradient_accumulation_steps": 1,
	// Learning Rate and Optimizer
	"learning_rate": 0.001,
	"lr_scheduler_type": "cosine_with_min_lr",
	"lr_scheduler_kwargs": {
	"min_lr_rate": 0.01
	},
	"warmup_ratio": 0.0,
	"adam_beta1": 0.9,
	"adam_beta2": 0.98,
	"grad_clip": 1.0,
	"weight_decay": 0.01,
	"optimizer": "muon",
	"muon_lr": 0.01,
	"muon_momentum": 0.95,
	// Logging
	"output_dir": "model_ckpts/alex_mp_20_text/",
	"save_total_limit": 2,
	"report_to": "wandb",
	"wandb_project_folder": "CrystaLLM-pi",
	"eval_strategy": "steps",
	"eval_steps": 10000,
	"logging_steps": 50,
	"save_strategy": "steps",
	"max_steps": 375000,
	"early_stopping_patience": 15,
	"early_stopping_threshold": 0.000005,
	// Utils
	"seed": 1,
	"data_seed": 1,
	"load_best_model_at_end": true,
	"metric_for_best_model": "eval_loss",
	"greater_is_better": false,
	"torch_compile": true,
	"deepspeed_config": "_config_files/deepspeed_default.json",

	// CodeCarbon Arguments
	//######################
	"codecarbon": true,
	"tracker_project": "CrystaLLM-pi"
	}