Instructions to use fableforge-ai/FableForge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fableforge-ai/FableForge with Transformers:

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

pipe = pipeline("text-generation", model="fableforge-ai/FableForge")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("fableforge-ai/FableForge")
model = AutoModelForMultimodalLM.from_pretrained("fableforge-ai/FableForge")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fableforge-ai/FableForge with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/fableforge-ai/FableForge

SGLang

How to use fableforge-ai/FableForge 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 "fableforge-ai/FableForge" \
    --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": "fableforge-ai/FableForge",
		"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 "fableforge-ai/FableForge" \
        --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": "fableforge-ai/FableForge",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fableforge-ai/FableForge with Docker Model Runner:
```
docker model run hf.co/fableforge-ai/FableForge
```

fix: add __type to token dicts, add tokenizer_class, fix Configuration Parsing Warning

by King3Djbl - opened 5 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-4

Files changed (1) hide show

tokenizer_config.json +8 -4

tokenizer_config.json CHANGED Viewed

@@ -7,28 +7,32 @@
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
-    "single_word": false
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
-    "single_word": false
   },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
-    "single_word": false
   },
   "pad_token": {
     "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
-    "single_word": false
   },
   "model_type": "llama",
   "model_max_length": 4096,

     "lstrip": false,
     "normalized": false,
     "rstrip": false,
+    "single_word": false,
+    "__type": "AddedToken"
   },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
+    "single_word": false,
+    "__type": "AddedToken"
   },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
+    "single_word": false,
+    "__type": "AddedToken"
   },
   "pad_token": {
     "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
+    "single_word": false,
+    "__type": "AddedToken"
   },
   "model_type": "llama",
   "model_max_length": 4096,