Instructions to use mrapacz/interlinear-en-greta-emb-auto-normalized-ob with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrapacz/interlinear-en-greta-emb-auto-normalized-ob with Transformers:

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

pipe = pipeline("text-generation", model="mrapacz/interlinear-en-greta-emb-auto-normalized-ob")

# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("mrapacz/interlinear-en-greta-emb-auto-normalized-ob", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mrapacz/interlinear-en-greta-emb-auto-normalized-ob with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mrapacz/interlinear-en-greta-emb-auto-normalized-ob

SGLang

How to use mrapacz/interlinear-en-greta-emb-auto-normalized-ob 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 "mrapacz/interlinear-en-greta-emb-auto-normalized-ob" \
    --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": "mrapacz/interlinear-en-greta-emb-auto-normalized-ob",
		"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 "mrapacz/interlinear-en-greta-emb-auto-normalized-ob" \
        --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": "mrapacz/interlinear-en-greta-emb-auto-normalized-ob",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mrapacz/interlinear-en-greta-emb-auto-normalized-ob with Docker Model Runner:
```
docker model run hf.co/mrapacz/interlinear-en-greta-emb-auto-normalized-ob
```

mrapacz commited on Feb 20, 2025

Commit

d997e87

verified ·

1 Parent(s): 07d8bf8

Upload MorphT5AutoForConditionalGeneration

Browse files

Files changed (2) hide show

config.json +6 -4
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "/net/tscratch/people/plgmrapacz/kairos/workspaces/exp512_2_INTMT-4879/best_model",
   "architectures": [
-    "MT5ForConditionalGeneration"
   ],
   "d_ff": 2048,
   "d_kv": 64,
@@ -16,7 +16,9 @@
   "is_encoder_decoder": true,
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
-  "model_type": "mt5",
   "num_decoder_layers": 12,
   "num_heads": 12,
   "num_layers": 12,
@@ -25,7 +27,7 @@
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
-  "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.31.0",
   "use_cache": true,

 {
+  "_name_or_path": "../workspaces/exp512_3_INTMT-5794/best_model",
   "architectures": [
+    "MorphT5AutoForConditionalGeneration"
   ],
   "d_ff": 2048,
   "d_kv": 64,
   "is_encoder_decoder": true,
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
+  "model_type": "morph-t5-auto",
+  "morph_compressed_embedding_size": 64,
+  "morph_vocabulary_size": 1074,
   "num_decoder_layers": 12,
   "num_heads": 12,
   "num_layers": 12,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
+  "tokenizer_class": "morpht5.tokenizer.morph_t5_tokenizer.MorphT5Tokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.31.0",
   "use_cache": true,

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bce1eb17ae2d1069442a6e1e75e9ae7af86f56816d4adae6ba05d485ac2227b9
-size 989655794

 version https://git-lfs.github.com/spec/v1
+oid sha256:6c32fd6db5f8d2959f3d611ec9bbf188507c15207bccf8b1e6150e9f875d9328
+size 990131262