Instructions to use obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def with Transformers:

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

pipe = pipeline("text-generation", model="obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def")
model = AutoModelForCausalLM.from_pretrained("obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def

SGLang

How to use obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def 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 "obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def" \
    --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": "obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def",
		"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 "obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def" \
        --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": "obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def with Docker Model Runner:
```
docker model run hf.co/obrmmk/tinycodellama-jp-0.6b-20k-2-instruct-jcodealpaca-py-def
```

obrmmk commited on Jan 14, 2024

Commit

d0bbece

verified ·

1 Parent(s): e91346e

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +29 -0

config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "_name_or_path": "NaoS2/tinycodellama-jp-0.6b-20k-2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 7,
+  "eos_token_id": 7,
+  "hidden_act": "silu",
+  "hidden_size": 1408,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 22,
+  "num_hidden_layers": 20,
+  "num_key_value_heads": 22,
+  "pad_token_id": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 50570
+}