Instructions to use Rocketknight1/gpt2-finetuned-wikitext2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rocketknight1/gpt2-finetuned-wikitext2 with Transformers:

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

pipe = pipeline("text-generation", model="Rocketknight1/gpt2-finetuned-wikitext2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Rocketknight1/gpt2-finetuned-wikitext2")
model = AutoModelForCausalLM.from_pretrained("Rocketknight1/gpt2-finetuned-wikitext2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Rocketknight1/gpt2-finetuned-wikitext2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rocketknight1/gpt2-finetuned-wikitext2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rocketknight1/gpt2-finetuned-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Rocketknight1/gpt2-finetuned-wikitext2

SGLang

How to use Rocketknight1/gpt2-finetuned-wikitext2 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 "Rocketknight1/gpt2-finetuned-wikitext2" \
    --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": "Rocketknight1/gpt2-finetuned-wikitext2",
		"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 "Rocketknight1/gpt2-finetuned-wikitext2" \
        --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": "Rocketknight1/gpt2-finetuned-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Rocketknight1/gpt2-finetuned-wikitext2 with Docker Model Runner:
```
docker model run hf.co/Rocketknight1/gpt2-finetuned-wikitext2
```

Rocketknight1 HF Staff commited on Jun 30, 2022

Commit

456b3c6

1 Parent(s): 0e32896

Training in progress epoch 0

Browse files

Files changed (5) hide show

README.md +7 -8
config.json +1 -1
special_tokens_map.json +5 -1
tf_model.h5 +1 -1
tokenizer_config.json +10 -1

README.md CHANGED Viewed

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 6.4978
-- Validation Loss: 6.3516
-- Epoch: 1
 ## Model description
@@ -42,13 +42,12 @@ The following hyperparameters were used during training:
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 7.3180     | 6.7701          | 0     |
-| 6.4978     | 6.3516          | 1     |
 ### Framework versions
-- Transformers 4.19.0.dev0
-- TensorFlow 2.8.0-rc0
-- Datasets 2.1.1.dev0
 - Tokenizers 0.11.0

 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 7.3123
+- Validation Loss: 6.7670
+- Epoch: 0
 ## Model description
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
+| 7.3123     | 6.7670          | 0     |
 ### Framework versions
+- Transformers 4.21.0.dev0
+- TensorFlow 2.9.1
+- Datasets 2.3.3.dev0
 - Tokenizers 0.11.0

config.json CHANGED Viewed

@@ -32,7 +32,7 @@
       "max_length": 50
     }
   },
-  "transformers_version": "4.19.0.dev0",
   "use_cache": true,
   "vocab_size": 50257
 }

       "max_length": 50
     }
   },
+  "transformers_version": "4.21.0.dev0",
   "use_cache": true,
   "vocab_size": 50257
 }

special_tokens_map.json CHANGED Viewed

	@@ -1 +1,5 @@
1	- {~~"bos_token": "<\|endoftext\|>", "eos_token": "<\|endoftext\|>", "unk_token": "<\|endoftext\|>"}~~

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

tf_model.h5 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:132c400c36da2261f2003983399adb78b02cc7a31470e45314366f3e888254f5
 size 497935464

 version https://git-lfs.github.com/spec/v1
+oid sha256:d58b5446148b73d2c8cfc62cc0990f00fd46a64a4e84e74b84749995333b1034
 size 497935464

tokenizer_config.json CHANGED Viewed

	@@ -1 +1,10 @@
1	- {"unk_token": "<\|endoftext\|>", "bos_token": "<\|endoftext\|>", "eos_token": "<\|endoftext\|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "sgugger/gpt2-like-tokenizer", "tokenizer_class": "GPT2Tokenizer"}

+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "sgugger/gpt2-like-tokenizer",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}