Instructions to use hf-internal-testing/tiny-random-bloom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-random-bloom with Transformers:

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

pipe = pipeline("text-generation", model="hf-internal-testing/tiny-random-bloom")

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/tiny-random-bloom")
model = AutoModel.from_pretrained("hf-internal-testing/tiny-random-bloom")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-internal-testing/tiny-random-bloom with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hf-internal-testing/tiny-random-bloom

SGLang

How to use hf-internal-testing/tiny-random-bloom 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 "hf-internal-testing/tiny-random-bloom" \
    --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": "hf-internal-testing/tiny-random-bloom",
		"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 "hf-internal-testing/tiny-random-bloom" \
        --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": "hf-internal-testing/tiny-random-bloom",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-internal-testing/tiny-random-bloom with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-random-bloom
```

Narsil commited on Jun 27, 2022

Commit

e8ce66e

verified ·

1 Parent(s): 450d632

Copy of `bigscience/bigscience-small-testing`

Browse files

Files changed (7) hide show

.gitattributes +1 -0
README.md +11 -0
config.json +29 -0
pytorch_model.bin +3 -0
special_tokens_map.json +1 -0
tokenizer.json +3 -0
tokenizer_config.json +1 -0

.gitattributes CHANGED Viewed

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,11 @@

+---
+language:
+  - eng
+tags:
+- integration
+pipeline_tag: text-generation
+---
+# BigScience - testing model
+This model aims to test the conversion between Megatron-LM and transformers. It is a small ```GPT-2```-like model that has been used to debug the script. Use it only for integration tests

config.json ADDED Viewed

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

+{
+  "_name_or_path": "/home/younes/Desktop/Work/data/megatron-debug/",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomModel"
+  ],
+  "attention_dropout": 0.1,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 0,
+  "hidden_dropout": 0.1,
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 2,
+  "pretraining_tp": 2,
+  "seq_length": 20,
+  "skip_bias_add": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.18.0.dev0",
+  "use_cache": false,
+  "vocab_size": 250880,
+  "slow_but_exact": true
+}

pytorch_model.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0e22bceb559a5fcdc3dbb0f9ea622210cbe6b2a56d459ad7693284a1e99569c8
+size 32322126

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer.json ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa39cd4b1500feb205bcce3b9703a4373414cafe4970e0657b413f7ddd2a9d3
+size 14500438

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"unk_token": "<unk>", "eos_token": "</s>", "bos_token": "<s>", "pad_token": "<pad>", "name_or_path": "bigscience/tokenizer", "special_tokens_map_file": null, "tokenizer_class": "BloomTokenizerFast"}