Instructions to use devlocalhost/hi-tinylama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use devlocalhost/hi-tinylama with Transformers:

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

pipe = pipeline("text-generation", model="devlocalhost/hi-tinylama")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("devlocalhost/hi-tinylama")
model = AutoModelForCausalLM.from_pretrained("devlocalhost/hi-tinylama")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use devlocalhost/hi-tinylama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/devlocalhost/hi-tinylama

SGLang

How to use devlocalhost/hi-tinylama 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 "devlocalhost/hi-tinylama" \
    --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": "devlocalhost/hi-tinylama",
		"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 "devlocalhost/hi-tinylama" \
        --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": "devlocalhost/hi-tinylama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use devlocalhost/hi-tinylama with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for devlocalhost/hi-tinylama to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for devlocalhost/hi-tinylama to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for devlocalhost/hi-tinylama to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="devlocalhost/hi-tinylama",
    max_seq_length=2048,
)

Docker Model Runner
How to use devlocalhost/hi-tinylama with Docker Model Runner:
```
docker model run hf.co/devlocalhost/hi-tinylama
```

devlocalhost commited on Feb 7, 2024

Commit

82e81fa

verified ·

1 Parent(s): 4cc46b8

Upload LlamaForCausalLM

Browse files

Files changed (3) hide show

config.json +33 -0
generation_config.json +7 -0
model.safetensors +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,33 @@

+{
+  "_name_or_path": "unsloth/tinyllama-bnb-4bit",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "linear"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "unsloth_version": "2024.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:464e6506e14e23aafa80ed0a647095b22ade1be49caefde1aa5364ebee2dc887
+size 2200119864