Instructions to use ayoolaolafenwa/ChatLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ayoolaolafenwa/ChatLM with Transformers:

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

pipe = pipeline("text-generation", model="ayoolaolafenwa/ChatLM", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ayoolaolafenwa/ChatLM", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ayoolaolafenwa/ChatLM", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ayoolaolafenwa/ChatLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ayoolaolafenwa/ChatLM

SGLang

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

Docker Model Runner
How to use ayoolaolafenwa/ChatLM with Docker Model Runner:
```
docker model run hf.co/ayoolaolafenwa/ChatLM
```

ayoolaolafenwa commited on Jun 22, 2023

Commit

0ce9b51

1 Parent(s): d2cf822

Upload RWForCausalLM

Browse files

Files changed (3) hide show

config.json +29 -0
generation_config.json +6 -0
pytorch_model.bin +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,29 @@

+{
+  "_name_or_path": "Falcon1BValModels_0",
+  "alibi": true,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "RWForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-rw-1b--configuration_RW.RWConfig",
+    "AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modelling_RW.RWForCausalLM"
+  },
+  "bias": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "RefinedWebModel",
+  "multi_query": false,
+  "n_head": 32,
+  "n_layer": 24,
+  "parallel_attn": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": false,
+  "vocab_size": 50304
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.30.2"
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2ee34512fceb92d9fdc5ea788d6467dda83bf62b261189627439b6410132d8
+size 5246595929