Instructions to use barbaroo/gptsw3-6.7B-translation-en-fo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use barbaroo/gptsw3-6.7B-translation-en-fo with Transformers:

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

pipe = pipeline("text-generation", model="barbaroo/gptsw3-6.7B-translation-en-fo")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("barbaroo/gptsw3-6.7B-translation-en-fo")
model = AutoModelForCausalLM.from_pretrained("barbaroo/gptsw3-6.7B-translation-en-fo", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use barbaroo/gptsw3-6.7B-translation-en-fo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "barbaroo/gptsw3-6.7B-translation-en-fo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "barbaroo/gptsw3-6.7B-translation-en-fo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/barbaroo/gptsw3-6.7B-translation-en-fo

SGLang

How to use barbaroo/gptsw3-6.7B-translation-en-fo 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 "barbaroo/gptsw3-6.7B-translation-en-fo" \
    --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": "barbaroo/gptsw3-6.7B-translation-en-fo",
		"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 "barbaroo/gptsw3-6.7B-translation-en-fo" \
        --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": "barbaroo/gptsw3-6.7B-translation-en-fo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use barbaroo/gptsw3-6.7B-translation-en-fo with Docker Model Runner:
```
docker model run hf.co/barbaroo/gptsw3-6.7B-translation-en-fo
```

barbaroo commited on Sep 2, 2025

Commit

c90a247

verified ·

1 Parent(s): b0f57ff

Refresh: aligned EOS/PAD + generation_config

Browse files

Files changed (3) hide show

config.json +1 -1
generation_config.json +1 -1
special_tokens_map.json +28 -4

config.json CHANGED Viewed

@@ -7,7 +7,7 @@
   "attn_pdrop": 0.1,
   "bos_token_id": 1,
   "embd_pdrop": 0.1,
-  "eos_token_id": 1,
   "initializer_range": 0.01,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",

   "attn_pdrop": 0.1,
   "bos_token_id": 1,
   "embd_pdrop": 0.1,
+  "eos_token_id": 3,
   "initializer_range": 0.01,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",

generation_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 1,
   "pad_token_id": 0,
   "transformers_version": "4.50.3"
 }

 {
   "_from_model_config": true,
   "bos_token_id": 1,
+  "eos_token_id": 3,
   "pad_token_id": 0,
   "transformers_version": "4.50.3"
 }

special_tokens_map.json CHANGED Viewed

@@ -1,6 +1,30 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
 }

 {
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }