Instructions to use bachephysicdun/HW2-supervised with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bachephysicdun/HW2-supervised with Transformers:

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

pipe = pipeline("text-generation", model="bachephysicdun/HW2-supervised")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bachephysicdun/HW2-supervised")
model = AutoModelForCausalLM.from_pretrained("bachephysicdun/HW2-supervised")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bachephysicdun/HW2-supervised with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bachephysicdun/HW2-supervised"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bachephysicdun/HW2-supervised",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bachephysicdun/HW2-supervised

SGLang

How to use bachephysicdun/HW2-supervised 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 "bachephysicdun/HW2-supervised" \
    --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": "bachephysicdun/HW2-supervised",
		"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 "bachephysicdun/HW2-supervised" \
        --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": "bachephysicdun/HW2-supervised",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bachephysicdun/HW2-supervised with Docker Model Runner:
```
docker model run hf.co/bachephysicdun/HW2-supervised
```

bachephysicdun commited on Aug 31, 2024

Commit

bbb831b

verified ·

1 Parent(s): 5c15a05

Training in progress, step 36

Browse files

Files changed (5) hide show

config.json +1 -0
model.safetensors +1 -1
special_tokens_map.json +1 -1
tokenizer_config.json +1 -1
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -17,6 +17,7 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "pad_token_id": 50256,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7ed3156f1a947f522bd4e90c9058fbc93efd5d5fc7f4bafb989d03c9ed13198
 size 497774208

 version https://git-lfs.github.com/spec/v1
+oid sha256:e66f9ff0694ec30b618a9e8d10d53248ff3417772db830548736ae05b2149db4
 size 497774208

special_tokens_map.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
-  "pad_token": "<p>",
   "unk_token": "<|endoftext|>"
 }

 {
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
   "unk_token": "<|endoftext|>"
 }

tokenizer_config.json CHANGED Viewed

@@ -14,7 +14,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
-  "pad_token": "<p>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }

   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7982434d1b7eb8d81f97233732f427d1fa54949d8b5749aa8d706257817e5299
 size 5432

 version https://git-lfs.github.com/spec/v1
+oid sha256:dde9e26f29c05c06278a9aa275e453c30f7cf5703ad8f7f0ad319cff3e619e8f
 size 5432