Instructions to use SaferChat/falcon7b-chat_omni with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SaferChat/falcon7b-chat_omni with Transformers:

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

pipe = pipeline("text-generation", model="SaferChat/falcon7b-chat_omni", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("SaferChat/falcon7b-chat_omni", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SaferChat/falcon7b-chat_omni with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SaferChat/falcon7b-chat_omni"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SaferChat/falcon7b-chat_omni",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SaferChat/falcon7b-chat_omni

SGLang

How to use SaferChat/falcon7b-chat_omni 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 "SaferChat/falcon7b-chat_omni" \
    --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": "SaferChat/falcon7b-chat_omni",
		"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 "SaferChat/falcon7b-chat_omni" \
        --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": "SaferChat/falcon7b-chat_omni",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SaferChat/falcon7b-chat_omni with Docker Model Runner:
```
docker model run hf.co/SaferChat/falcon7b-chat_omni
```

SaferChat commited on Jul 26, 2023

Commit

fffd3ff

1 Parent(s): 022dabf

Update config.json

Browse files

Files changed (1) hide show

config.json +6 -6

config.json CHANGED Viewed

@@ -7,12 +7,12 @@
   ],
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "tiiuae/falcon-7b--configuration_RW.RWConfig",
-    "AutoModel": "tiiuae/falcon-7b--modelling_RW.RWModel",
-    "AutoModelForCausalLM": "tiiuae/falcon-7b--modelling_RW.RWForCausalLM",
-    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modelling_RW.RWForQuestionAnswering",
-    "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modelling_RW.RWForSequenceClassification",
-    "AutoModelForTokenClassification": "tiiuae/falcon-7b--modelling_RW.RWForTokenClassification"
   },
   "bias": false,
   "bos_token_id": 11,

   ],
   "attention_dropout": 0.0,
   "auto_map": {
+    "AutoConfig": "configuration_RW.RWConfig",
+    "AutoModel": "modelling_RW.RWModel",
+    "AutoModelForCausalLM": "modelling_RW.RWForCausalLM",
+    "AutoModelForQuestionAnswering": "modelling_RW.RWForQuestionAnswering",
+    "AutoModelForSequenceClassification": "modelling_RW.RWForSequenceClassification",
+    "AutoModelForTokenClassification": "modelling_RW.RWForTokenClassification"
   },
   "bias": false,
   "bos_token_id": 11,