Instructions to use mafgit/empathetic-distilgpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mafgit/empathetic-distilgpt2 with Transformers:

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

pipe = pipeline("text-generation", model="mafgit/empathetic-distilgpt2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mafgit/empathetic-distilgpt2")
model = AutoModelForCausalLM.from_pretrained("mafgit/empathetic-distilgpt2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mafgit/empathetic-distilgpt2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mafgit/empathetic-distilgpt2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mafgit/empathetic-distilgpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mafgit/empathetic-distilgpt2

SGLang

How to use mafgit/empathetic-distilgpt2 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 "mafgit/empathetic-distilgpt2" \
    --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": "mafgit/empathetic-distilgpt2",
		"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 "mafgit/empathetic-distilgpt2" \
        --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": "mafgit/empathetic-distilgpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mafgit/empathetic-distilgpt2 with Docker Model Runner:
```
docker model run hf.co/mafgit/empathetic-distilgpt2
```

mafgit commited on Apr 30

Commit

1f58c19

verified ·

1 Parent(s): 1b76f52

Training in progress, epoch 1

Browse files

Files changed (6) hide show

config.json +2 -2
generation_config.json +1 -1
model.safetensors +2 -2
tokenizer.json +9 -0
tokenizer_config.json +1 -1
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -25,7 +25,7 @@
   "n_inner": null,
   "n_layer": 6,
   "n_positions": 1024,
-  "pad_token_id": 50256,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -44,5 +44,5 @@
   "tie_word_embeddings": true,
   "transformers_version": "5.0.0",
   "use_cache": false,
-  "vocab_size": 50257
 }

   "n_inner": null,
   "n_layer": 6,
   "n_positions": 1024,
+  "pad_token_id": 50257,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
   "tie_word_embeddings": true,
   "transformers_version": "5.0.0",
   "use_cache": false,
+  "vocab_size": 50258
 }

generation_config.json CHANGED Viewed

@@ -4,6 +4,6 @@
   "eos_token_id": [
     50256
   ],
-  "pad_token_id": 50256,
   "transformers_version": "5.0.0"
 }

   "eos_token_id": [
     50256
   ],
+  "pad_token_id": 50257,
   "transformers_version": "5.0.0"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:256fb0f2f5441cb69270c89265c6faf3c537c7789d75dcda31209ed3ea1f52e0
-size 327657928

 version https://git-lfs.github.com/spec/v1
+oid sha256:c95f8bc47b606f61257d0d9a89fe051f10cde881d934a8b07bad9c164f63add2
+size 327661000

tokenizer.json CHANGED Viewed

@@ -16,6 +16,15 @@
       "rstrip": false,
       "normalized": true,
       "special": true
     }
   ],
   "normalizer": null,

       "rstrip": false,
       "normalized": true,
       "special": true
+    },
+    {
+      "id": 50257,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json CHANGED Viewed

@@ -6,7 +6,7 @@
   "errors": "replace",
   "is_local": false,
   "model_max_length": 1024,
-  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }

   "errors": "replace",
   "is_local": false,
   "model_max_length": 1024,
+  "pad_token": "[PAD]",
   "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:fc4c4516918aaff33701f20cb63684314f3d9f720a44c14e611f0248ebf16c0f
 size 5201

 version https://git-lfs.github.com/spec/v1
+oid sha256:87671058d8d779a3cc26bb1ff72d7aa2c5cf2670c04b701da62c0e69fceebc4d
 size 5201