Instructions to use rahuldshetty/tinyllama-python with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rahuldshetty/tinyllama-python with Transformers:

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

pipe = pipeline("text-generation", model="rahuldshetty/tinyllama-python")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rahuldshetty/tinyllama-python")
model = AutoModelForCausalLM.from_pretrained("rahuldshetty/tinyllama-python")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rahuldshetty/tinyllama-python with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/rahuldshetty/tinyllama-python

SGLang

How to use rahuldshetty/tinyllama-python 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 "rahuldshetty/tinyllama-python" \
    --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": "rahuldshetty/tinyllama-python",
		"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 "rahuldshetty/tinyllama-python" \
        --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": "rahuldshetty/tinyllama-python",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rahuldshetty/tinyllama-python with Docker Model Runner:
```
docker model run hf.co/rahuldshetty/tinyllama-python
```

rahuldshetty commited on Jan 19, 2024

Commit

0d0f874

verified ·

1 Parent(s): 6ee7eb6

Delete config.json

Browse files

Files changed (1) hide show

config.json +0 -45

config.json DELETED Viewed

@@ -1,45 +0,0 @@
-{
-  "_name_or_path": "unsloth/tinyllama",
-  "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,
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": "null",
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "factor": 2.0,
-    "type": "linear"
-  },
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.37.0.dev0",
-  "unsloth_version": "2024.1",
-  "use_cache": true,
-  "vocab_size": 32000
-}