Instructions to use yujiepan/stablelm-2-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yujiepan/stablelm-2-tiny-random with Transformers:

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

pipe = pipeline("text-generation", model="yujiepan/stablelm-2-tiny-random", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yujiepan/stablelm-2-tiny-random")
model = AutoModelForCausalLM.from_pretrained("yujiepan/stablelm-2-tiny-random", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yujiepan/stablelm-2-tiny-random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yujiepan/stablelm-2-tiny-random"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yujiepan/stablelm-2-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yujiepan/stablelm-2-tiny-random

SGLang

How to use yujiepan/stablelm-2-tiny-random 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 "yujiepan/stablelm-2-tiny-random" \
    --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": "yujiepan/stablelm-2-tiny-random",
		"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 "yujiepan/stablelm-2-tiny-random" \
        --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": "yujiepan/stablelm-2-tiny-random",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yujiepan/stablelm-2-tiny-random with Docker Model Runner:
```
docker model run hf.co/yujiepan/stablelm-2-tiny-random
```

yujiepan commited on Mar 30, 2024

Commit

fa8f8db

verified ·

1 Parent(s): fde817e

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

README.md +1 -37
config.json +1 -1
model.safetensors +2 -2

README.md CHANGED Viewed

@@ -13,41 +13,5 @@ Note the model is in float16.
 Codes:
 ```python
-import transformers
-import torch
-import os
-from huggingface_hub import create_repo, upload_folder
-source_model_id = 'stabilityai/stablelm-2-1_6b'
-save_path = '/tmp/yujiepan/stablelm-2-tiny-random'
-repo_id = 'yujiepan/stablelm-2-tiny-random'
-config = transformers.AutoConfig.from_pretrained(
-    source_model_id, trust_remote_code=True)
-config.hidden_size = 4
-config.intermediate_size = 6
-config.num_attention_heads = 4
-config.num_hidden_layers = 2
-config.num_key_value_heads = 2
-config.torch_dtype = torch.float16
-model = transformers.AutoModelForCausalLM.from_config(
-    config, trust_remote_code=True, torch_dtype=torch.float16)
-model = model.half()
-print(next(iter(model.parameters())).dtype)
-model.config.torch_dtype = torch.float16
-tokenizer = transformers.AutoTokenizer.from_pretrained(
-    source_model_id, trust_remote_code=True)
-result = transformers.pipelines.pipeline(
-    'text-generation',
-    model=model.float(), tokenizer=tokenizer)('Hello World!')
-print(result)
-model.save_pretrained(save_path)
-tokenizer.save_pretrained(save_path)
-os.system(f'ls -alh {save_path}')
-# create_repo(repo_id, exist_ok=True)
-# upload_folder(repo_id=repo_id, folder_path=save_path)
 ```

 Codes:
 ```python
+model.config
 ```

config.json CHANGED Viewed

@@ -21,7 +21,7 @@
   "rope_scaling": null,
   "rope_theta": 10000,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
   "transformers_version": "4.39.0",
   "use_cache": true,
   "use_qkv_bias": true,

   "rope_scaling": null,
   "rope_theta": 10000,
   "tie_word_embeddings": false,
+  "torch_dtype": "float16",
   "transformers_version": "4.39.0",
   "use_cache": true,
   "use_qkv_bias": true,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b31730a65c0a5975358dce3ab7fa6e96aeff6acd6bdcdabf75dc60ada7644a8
-size 3215696

 version https://git-lfs.github.com/spec/v1
+oid sha256:00257f3077b772910186736a9f5760978bbcfacca5e20ceb6ad6af885294be80
+size 1609472