Instructions to use EleutherAI/pythia-2.8b-modularaddition-first-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EleutherAI/pythia-2.8b-modularaddition-first-ft with Transformers:

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

pipe = pipeline("text-generation", model="EleutherAI/pythia-2.8b-modularaddition-first-ft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EleutherAI/pythia-2.8b-modularaddition-first-ft")
model = AutoModelForCausalLM.from_pretrained("EleutherAI/pythia-2.8b-modularaddition-first-ft")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use EleutherAI/pythia-2.8b-modularaddition-first-ft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EleutherAI/pythia-2.8b-modularaddition-first-ft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EleutherAI/pythia-2.8b-modularaddition-first-ft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EleutherAI/pythia-2.8b-modularaddition-first-ft

SGLang

How to use EleutherAI/pythia-2.8b-modularaddition-first-ft 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 "EleutherAI/pythia-2.8b-modularaddition-first-ft" \
    --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": "EleutherAI/pythia-2.8b-modularaddition-first-ft",
		"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 "EleutherAI/pythia-2.8b-modularaddition-first-ft" \
        --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": "EleutherAI/pythia-2.8b-modularaddition-first-ft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EleutherAI/pythia-2.8b-modularaddition-first-ft with Docker Model Runner:
```
docker model run hf.co/EleutherAI/pythia-2.8b-modularaddition-first-ft
```

norabelrose commited on Mar 22, 2024

Commit

20f4089

verified ·

1 Parent(s): 63730f9

Upload tokenizer

Browse files

Files changed (2) hide show

special_tokens_map.json +7 -1
tokenizer_config.json +4 -0

special_tokens_map.json CHANGED Viewed

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

     "rstrip": false,
     "single_word": false
   },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_config.json CHANGED Viewed

@@ -205,8 +205,12 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }

   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 1024,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
+  "stride": 0,
   "tokenizer_class": "GPTNeoXTokenizer",
+  "truncation_side": "left",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }