Instructions to use Dracones/c4ai-command-r-plus_exl2_5.5bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dracones/c4ai-command-r-plus_exl2_5.5bpw with Transformers:

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

pipe = pipeline("text-generation", model="Dracones/c4ai-command-r-plus_exl2_5.5bpw")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Dracones/c4ai-command-r-plus_exl2_5.5bpw")
model = AutoModelForCausalLM.from_pretrained("Dracones/c4ai-command-r-plus_exl2_5.5bpw", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dracones/c4ai-command-r-plus_exl2_5.5bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dracones/c4ai-command-r-plus_exl2_5.5bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dracones/c4ai-command-r-plus_exl2_5.5bpw",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Dracones/c4ai-command-r-plus_exl2_5.5bpw

SGLang

How to use Dracones/c4ai-command-r-plus_exl2_5.5bpw 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 "Dracones/c4ai-command-r-plus_exl2_5.5bpw" \
    --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": "Dracones/c4ai-command-r-plus_exl2_5.5bpw",
		"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 "Dracones/c4ai-command-r-plus_exl2_5.5bpw" \
        --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": "Dracones/c4ai-command-r-plus_exl2_5.5bpw",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Dracones/c4ai-command-r-plus_exl2_5.5bpw with Docker Model Runner:
```
docker model run hf.co/Dracones/c4ai-command-r-plus_exl2_5.5bpw
```

Dracones commited on Apr 13, 2024

Commit

5c41012

verified ·

1 Parent(s): f1ddb34

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +5 -2

README.md CHANGED Viewed

@@ -41,6 +41,7 @@ Below are the perplexity scores for the EXL2 models. A lower score is better.
 | Quant Level | Perplexity Score | Repo |
 |-------------|------------------|------|
 | 6.0 | 4.7068 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
 | 5.0 | 4.7309 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
 | 4.5 | 4.8111 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
 | 4.25 | 4.8292 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
@@ -49,9 +50,10 @@ Below are the perplexity scores for the EXL2 models. A lower score is better.
 | 3.5 | 4.9592 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
 | 3.25 | 5.0631 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
 | 3.0 | 5.2050 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
 | 2.5 | 5.6681 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
-_TODO:_ Dracones quant perplexity scores being worked on.
 ## EQ Bench
@@ -60,10 +62,11 @@ Here are the EQ Bench scores for the EXL2 quants using Alpaca, ChatML, Command-R
 | Quant Size | Alpaca | ChatML | Command-R | Command-R-Plus |
 |------------|--------|--------|--------|--------|
 | 6.0 | 70.77 | 62.58 | 75.81 | 74.95 |
 | 5.0 | 69.51 | 63.94 | 74.92 | 75.28 |
-_TODO:_ EQ Bench scores being worked on.
 ### Command-R-Plus Template

 | Quant Level | Perplexity Score | Repo |
 |-------------|------------------|------|
 | 6.0 | 4.7068 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
+| 5.5 | 4.7136 | Dracones |
 | 5.0 | 4.7309 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
 | 4.5 | 4.8111 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
 | 4.25 | 4.8292 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
 | 3.5 | 4.9592 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
 | 3.25 | 5.0631 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
 | 3.0 | 5.2050 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
+| 2.75 | 5.3820 | Dracones |
 | 2.5 | 5.6681 | [turboderp](https://huggingface.co/turboderp/command-r-plus-103B-exl2) |
+| 2.25 | 5.9769 | Dracones |
 ## EQ Bench
 | Quant Size | Alpaca | ChatML | Command-R | Command-R-Plus |
 |------------|--------|--------|--------|--------|
 | 6.0 | 70.77 | 62.58 | 75.81 | 74.95 |
+| 5.5 | 71.93 | 67.7 | 74.9 | 75.48 |
 | 5.0 | 69.51 | 63.94 | 74.92 | 75.28 |
+_Note:_ EQ Bench scripting not working well, other quants may not be tested.
 ### Command-R-Plus Template