Instructions to use shuyuej/Command-R-Smaller-HF-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shuyuej/Command-R-Smaller-HF-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="shuyuej/Command-R-Smaller-HF-GPTQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shuyuej/Command-R-Smaller-HF-GPTQ")
model = AutoModelForCausalLM.from_pretrained("shuyuej/Command-R-Smaller-HF-GPTQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use shuyuej/Command-R-Smaller-HF-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shuyuej/Command-R-Smaller-HF-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shuyuej/Command-R-Smaller-HF-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shuyuej/Command-R-Smaller-HF-GPTQ

SGLang

How to use shuyuej/Command-R-Smaller-HF-GPTQ 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 "shuyuej/Command-R-Smaller-HF-GPTQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shuyuej/Command-R-Smaller-HF-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "shuyuej/Command-R-Smaller-HF-GPTQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shuyuej/Command-R-Smaller-HF-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shuyuej/Command-R-Smaller-HF-GPTQ with Docker Model Runner:
```
docker model run hf.co/shuyuej/Command-R-Smaller-HF-GPTQ
```

shuyuej commited on Jul 23, 2024

Commit

7d7c60e

verified ·

1 Parent(s): 6a0c8e3

Update README.md

Browse files

Files changed (1) hide show

README.md +45 -1

README.md CHANGED Viewed

@@ -1,3 +1,47 @@
 ---
 license: apache-2.0
----

 ---
 license: apache-2.0
+---
+# The Quantized Command R Model
+Original Base Model: `CohereForAI/c4ai-command-r-v01`.<br>
+Link: [https://huggingface.co/CohereForAI/c4ai-command-r-v01](https://huggingface.co/CohereForAI/c4ai-command-r-v01)
+## Special Notice
+(1) Please note the model is quantized by utilizing the `AutoModelForCausalLM.from_pretrained` in the `transformers` package.
+(2) For the model quantized by `auto-gptq` package, please check the link here: [https://huggingface.co/shuyuej/Command-R-GPTQ](https://huggingface.co/shuyuej/Command-R-GPTQ).
+(3) This one is a smaller one by setting `group_size=1024`.
+## Quantization Configurations
+```
+"quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": null,
+    "cache_block_outputs": true,
+    "damp_percent": 0.1,
+    "dataset": null,
+    "desc_act": false,
+    "exllama_config": {
+      "version": 1
+    },
+    "group_size": 1024,
+    "max_input_length": null,
+    "model_seqlen": null,
+    "module_name_preceding_first_block": null,
+    "modules_in_block_to_quantize": null,
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": false,
+    "use_exllama": true
+  },
+```
+## Source Codes
+Source Codes: [https://github.com/vkola-lab/medpodgpt/tree/main/quantization](https://github.com/vkola-lab/medpodgpt/tree/main/quantization).