Instructions to use SlayerLab/GoLLeM-110M-PL-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SlayerLab/GoLLeM-110M-PL-v3 with Transformers:

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

pipe = pipeline("text-generation", model="SlayerLab/GoLLeM-110M-PL-v3")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SlayerLab/GoLLeM-110M-PL-v3")
model = AutoModelForCausalLM.from_pretrained("SlayerLab/GoLLeM-110M-PL-v3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SlayerLab/GoLLeM-110M-PL-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SlayerLab/GoLLeM-110M-PL-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SlayerLab/GoLLeM-110M-PL-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SlayerLab/GoLLeM-110M-PL-v3

SGLang

How to use SlayerLab/GoLLeM-110M-PL-v3 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 "SlayerLab/GoLLeM-110M-PL-v3" \
    --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": "SlayerLab/GoLLeM-110M-PL-v3",
		"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 "SlayerLab/GoLLeM-110M-PL-v3" \
        --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": "SlayerLab/GoLLeM-110M-PL-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SlayerLab/GoLLeM-110M-PL-v3 with Docker Model Runner:
```
docker model run hf.co/SlayerLab/GoLLeM-110M-PL-v3
```

Maggio33 commited on Aug 30

Commit

2d69f4f

verified ·

1 Parent(s): 0009da0

card: attach structured model-index (board-repro benchmarks, 7 tasks)

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -19,11 +19,11 @@ model-index:
   - task: {type: text-classification, name: PolEmo2-IN sentiment}
     dataset: {type: allegro/klej-polemo2-in, name: PolEmo2-IN}
     metrics:
-    - {type: accuracy, value: 18.0, name: accuracy (0-shot, domain-PMI board-repro)}
   - task: {type: text-classification, name: 8TAGS topic}
     dataset: {type: sdadas/8tags, name: 8TAGS}
     metrics:
-    - {type: accuracy, value: 41.2, name: accuracy (0-shot, domain-PMI board-repro)}
   - task: {type: multiple-choice, name: Belebele PL reading}
     dataset: {type: facebook/belebele, name: Belebele pol_Latn}
     metrics:
@@ -31,19 +31,19 @@ model-index:
   - task: {type: text-classification, name: CBD cyberbullying}
     dataset: {type: ptaszynski/PolishCyberbullyingDataset, name: CBD}
     metrics:
-    - {type: f1, value: 12.6, name: macro-F1 (0-shot, domain-PMI board-repro)}
   - task: {type: text-classification, name: DYK question-answer}
     dataset: {type: allegro/klej-dyk, name: DYK}
     metrics:
-    - {type: f1, value: 28.3, name: positive-F1 (0-shot, domain-PMI board-repro)}
   - task: {type: token-classification, name: KLEJ NER}
     dataset: {type: allegro/klej-nkjp-ner, name: KLEJ-NER}
     metrics:
-    - {type: accuracy, value: 18.2, name: accuracy (0-shot, domain-PMI board-repro)}
   - task: {type: text-classification, name: PSC summary}
     dataset: {type: allegro/klej-psc, name: PSC}
     metrics:
-    - {type: f1, value: 44.2, name: positive-F1 (0-shot, domain-PMI board-repro)}
 ---
 # GoLLeM-110M-PL-v3

   - task: {type: text-classification, name: PolEmo2-IN sentiment}
     dataset: {type: allegro/klej-polemo2-in, name: PolEmo2-IN}
     metrics:
+    - {type: accuracy, value: 18.0, name: accuracy (0-shot; domain-PMI board-repro)}
   - task: {type: text-classification, name: 8TAGS topic}
     dataset: {type: sdadas/8tags, name: 8TAGS}
     metrics:
+    - {type: accuracy, value: 41.2, name: accuracy (0-shot; domain-PMI board-repro)}
   - task: {type: multiple-choice, name: Belebele PL reading}
     dataset: {type: facebook/belebele, name: Belebele pol_Latn}
     metrics:
   - task: {type: text-classification, name: CBD cyberbullying}
     dataset: {type: ptaszynski/PolishCyberbullyingDataset, name: CBD}
     metrics:
+    - {type: f1, value: 12.6, name: macro-F1 (0-shot; domain-PMI board-repro)}
   - task: {type: text-classification, name: DYK question-answer}
     dataset: {type: allegro/klej-dyk, name: DYK}
     metrics:
+    - {type: f1, value: 28.3, name: positive-F1 (0-shot; domain-PMI board-repro)}
   - task: {type: token-classification, name: KLEJ NER}
     dataset: {type: allegro/klej-nkjp-ner, name: KLEJ-NER}
     metrics:
+    - {type: accuracy, value: 18.2, name: accuracy (0-shot; domain-PMI board-repro)}
   - task: {type: text-classification, name: PSC summary}
     dataset: {type: allegro/klej-psc, name: PSC}
     metrics:
+    - {type: f1, value: 44.2, name: positive-F1 (0-shot; domain-PMI board-repro)}
 ---
 # GoLLeM-110M-PL-v3