Instructions to use evilfreelancer/dostoevsky_doesnt_write_it_gpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use evilfreelancer/dostoevsky_doesnt_write_it_gpt2 with Transformers:

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

pipe = pipeline("text-generation", model="evilfreelancer/dostoevsky_doesnt_write_it_gpt2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("evilfreelancer/dostoevsky_doesnt_write_it_gpt2")
model = AutoModelForCausalLM.from_pretrained("evilfreelancer/dostoevsky_doesnt_write_it_gpt2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use evilfreelancer/dostoevsky_doesnt_write_it_gpt2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "evilfreelancer/dostoevsky_doesnt_write_it_gpt2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "evilfreelancer/dostoevsky_doesnt_write_it_gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/evilfreelancer/dostoevsky_doesnt_write_it_gpt2

SGLang

How to use evilfreelancer/dostoevsky_doesnt_write_it_gpt2 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 "evilfreelancer/dostoevsky_doesnt_write_it_gpt2" \
    --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": "evilfreelancer/dostoevsky_doesnt_write_it_gpt2",
		"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 "evilfreelancer/dostoevsky_doesnt_write_it_gpt2" \
        --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": "evilfreelancer/dostoevsky_doesnt_write_it_gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use evilfreelancer/dostoevsky_doesnt_write_it_gpt2 with Docker Model Runner:
```
docker model run hf.co/evilfreelancer/dostoevsky_doesnt_write_it_gpt2
```

Paul Rock commited on Feb 18, 2023

Commit

24f91df

1 Parent(s): f1ef1a4

Convertation

Browse files

Files changed (3) hide show

config.json +1 -3
eval_results.txt +0 -1
training_args.bin +0 -3

config.json CHANGED Viewed

@@ -13,7 +13,6 @@
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "finetuning_task": null,
-  "gradient_checkpointing": false,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1"
@@ -33,7 +32,6 @@
   "n_ctx": 2048,
   "n_embd": 768,
   "n_head": 12,
-  "n_inner": null,
   "n_layer": 12,
   "n_positions": 2048,
   "no_repeat_ngram_size": 0,
@@ -58,5 +56,5 @@
   "top_p": 1.0,
   "torchscript": false,
   "use_bfloat16": false,
-  "vocab_size": 50257
 }

   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "finetuning_task": null,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1"
   "n_ctx": 2048,
   "n_embd": 768,
   "n_head": 12,
   "n_layer": 12,
   "n_positions": 2048,
   "no_repeat_ngram_size": 0,
   "top_p": 1.0,
   "torchscript": false,
   "use_bfloat16": false,
+  "vocab_size": 50264
 }

eval_results.txt DELETED Viewed

	@@ -1 +0,0 @@
1	- perplexity = tensor(22.6912)

training_args.bin DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9467dc68dd9d879ebb53e9025f9429f10b3e2707746718674988122f8bb048ea
-size 1595