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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

sgugger commited on Mar 28, 2023

Commit

06fdc8b

1 Parent(s): 95dc5c5

Upload tiny models for XGLMForCausalLM

Browse files

Files changed (8) hide show

.gitattributes +1 -0
config.json +3 -3
generation_config.json +8 -0
pytorch_model.bin +2 -2
sentencepiece.bpe.model +3 -0
tf_model.h5 +2 -2
tokenizer.json +0 -0
tokenizer_config.json +1 -1

.gitattributes CHANGED Viewed

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

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

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "temp/dummy/xglm/XGLMForCausalLM",
   "activation_dropout": 0.1,
   "activation_function": "gelu",
   "architectures": [
@@ -24,7 +24,7 @@
   "pad_token_id": 1,
   "scale_embedding": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.25.0.dev0",
   "use_cache": true,
-  "vocab_size": 1024
 }

 {
+  "_name_or_path": "tiny_models/xglm/XGLMForCausalLM",
   "activation_dropout": 0.1,
   "activation_function": "gelu",
   "architectures": [
   "pad_token_id": 1,
   "scale_embedding": true,
   "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
   "use_cache": true,
+  "vocab_size": 256008
 }

generation_config.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:716441d567fd6aa8807b5ee1f8a312324a8ef276c8a4da6999276cba10e82d14
-size 292714

 version https://git-lfs.github.com/spec/v1
+oid sha256:912f768c127c4827b85180eab2e52532ffd445a8169af40814f917a1175233ca
+size 32930730

sentencepiece.bpe.model ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c49dc7e82c10227af764e518924cf2f9d50c00462750d184fa74697bba65eef8
+size 4920706

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f8d5af1b7033f94eab5e5fe562f25b08c70fc4c17206d209c37577b6d4b404b
-size 560936

 version https://git-lfs.github.com/spec/v1
+oid sha256:fa7859c92ab4d337edc06597e5637c9de7ecb7f64746b60d5e6008461495bfb1
+size 65836840

tokenizer.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -12,11 +12,11 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "model_max_length": 512,
-  "name_or_path": "facebook/xglm-564M",
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
   "special_tokens_map_file": "hf_models/xglm-564M/special_tokens_map.json",
   "tokenizer_class": "XGLMTokenizer",
   "unk_token": "<unk>"
 }

   "cls_token": "<s>",
   "eos_token": "</s>",
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
   "special_tokens_map_file": "hf_models/xglm-564M/special_tokens_map.json",
   "tokenizer_class": "XGLMTokenizer",
+  "tokenizer_file": null,
   "unk_token": "<unk>"
 }