Instructions to use pretraining/krill-e2e-ci-pico with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pretraining/krill-e2e-ci-pico with Transformers:

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

pipe = pipeline("text-generation", model="pretraining/krill-e2e-ci-pico")

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

tokenizer = AutoTokenizer.from_pretrained("pretraining/krill-e2e-ci-pico")
model = AutoModelForCausalLM.from_pretrained("pretraining/krill-e2e-ci-pico", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pretraining/krill-e2e-ci-pico with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pretraining/krill-e2e-ci-pico"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pretraining/krill-e2e-ci-pico",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pretraining/krill-e2e-ci-pico

SGLang

How to use pretraining/krill-e2e-ci-pico 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 "pretraining/krill-e2e-ci-pico" \
    --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": "pretraining/krill-e2e-ci-pico",
		"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 "pretraining/krill-e2e-ci-pico" \
        --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": "pretraining/krill-e2e-ci-pico",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pretraining/krill-e2e-ci-pico with Docker Model Runner:
```
docker model run hf.co/pretraining/krill-e2e-ci-pico
```

minpeter commited on Aug 9, 2025

Commit

4e3e945

verified ·

1 Parent(s): 52934ee

Training in progress, step 44

Browse files

Files changed (3) hide show

config.json +30 -0
model.safetensors +3 -0
training_args.bin +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 31989,
+  "eos_token_id": 31989,
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pad_token_id": 31989,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:760a495e6e75cd0adf8ab8e03564e40222a2e467695d093abd3866f52ef681ab
+size 2066752

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f66eab1b01c0b82bf9b7475388095bb05cad05de503d29aabfbe91b4815cf22c
+size 5777