Instructions to use Multi-Domain-Expert-Learning/expert-min-pile-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Multi-Domain-Expert-Learning/expert-min-pile-instruct with Transformers:

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

pipe = pipeline("text-generation", model="Multi-Domain-Expert-Learning/expert-min-pile-instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Multi-Domain-Expert-Learning/expert-min-pile-instruct")
model = AutoModelForCausalLM.from_pretrained("Multi-Domain-Expert-Learning/expert-min-pile-instruct")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Multi-Domain-Expert-Learning/expert-min-pile-instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Multi-Domain-Expert-Learning/expert-min-pile-instruct

SGLang

How to use Multi-Domain-Expert-Learning/expert-min-pile-instruct 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 "Multi-Domain-Expert-Learning/expert-min-pile-instruct" \
    --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": "Multi-Domain-Expert-Learning/expert-min-pile-instruct",
		"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 "Multi-Domain-Expert-Learning/expert-min-pile-instruct" \
        --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": "Multi-Domain-Expert-Learning/expert-min-pile-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Multi-Domain-Expert-Learning/expert-min-pile-instruct with Docker Model Runner:
```
docker model run hf.co/Multi-Domain-Expert-Learning/expert-min-pile-instruct
```

P1ayer-1 commited on May 8, 2023

Commit

cc05141

1 Parent(s): 3359129

Training in progress, step 500

Browse files

Files changed (4) hide show

config.json +1 -1
pytorch_model.bin +2 -2
tokenizer.json +0 -1
training_args.bin +2 -2

config.json CHANGED Viewed

@@ -17,7 +17,7 @@
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
   "transformers_version": "4.28.1",
   "use_cache": true,
   "use_parallel_residual": true,

   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
+  "torch_dtype": "float16",
   "transformers_version": "4.28.1",
   "use_cache": true,
   "use_parallel_residual": true,

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e594dbaa75c36cbf7e4a34fe357363421b8aad7ae231521896723339cfe504d5
-size 4113910045

 version https://git-lfs.github.com/spec/v1
+oid sha256:8f8c41c9a4671e776bc28d3049a1477671e4e02c85575d05c7cddb103acf3e05
+size 2090538933

tokenizer.json CHANGED Viewed

@@ -275,7 +275,6 @@
     "continuing_subword_prefix": null,
     "end_of_word_suffix": null,
     "fuse_unk": false,
-    "byte_fallback": false,
     "vocab": {
       "<|endoftext|>": 0,
       "<|padding|>": 1,

     "continuing_subword_prefix": null,
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "vocab": {
       "<|endoftext|>": 0,
       "<|padding|>": 1,

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d7a9f8dc6992869b75949cdfa8dbd7afe456ee4f5e8f4f6f4ac3864cc9a00aa
-size 3771

 version https://git-lfs.github.com/spec/v1
+oid sha256:49c48fe5038ba9667ac6ed496df6b0e3a7ac8168ab8c61b40b1a0a663158f631
+size 4795