Instructions to use nitky/Megac4ai-command-r-plus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nitky/Megac4ai-command-r-plus with Transformers:

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

pipe = pipeline("text-generation", model="nitky/Megac4ai-command-r-plus")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nitky/Megac4ai-command-r-plus")
model = AutoModelForCausalLM.from_pretrained("nitky/Megac4ai-command-r-plus")
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 Settings

vLLM

How to use nitky/Megac4ai-command-r-plus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nitky/Megac4ai-command-r-plus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nitky/Megac4ai-command-r-plus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nitky/Megac4ai-command-r-plus

SGLang

How to use nitky/Megac4ai-command-r-plus 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 "nitky/Megac4ai-command-r-plus" \
    --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": "nitky/Megac4ai-command-r-plus",
		"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 "nitky/Megac4ai-command-r-plus" \
        --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": "nitky/Megac4ai-command-r-plus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nitky/Megac4ai-command-r-plus with Docker Model Runner:
```
docker model run hf.co/nitky/Megac4ai-command-r-plus
```

Which Mergekit did you use for this?

by softwareweaver - opened Jun 15, 2024

Discussion

softwareweaver

Jun 15, 2024

Which Mergekit did you use for this? The standard one did not work. Thanks.

nitky

Owner Jun 15, 2024

That's completely correct.

Mergekit has two issues to merge CohereForAI/c4ai-command-r-plus.

The layers added in c4ai-command-r-plus is not supported.
The lm_head section on cohere.json causes an unsupported model in llama.cpp.

So I wrote a patch for these issues:

--- a/mergekit/_data/architectures/cohere.json
+++ b/mergekit/_data/architectures/cohere.json
@@ -12,13 +12,6 @@
     "post_weights": [
         {
             "name": "model.norm.weight"
-        },
-        {
-            "name": "lm_head.weight",
-            "is_embed": true,
-            "aliases": [
-                "model.embed_tokens.weight"
-            ]
         }
     ],
     "num_layers_config_key": "num_hidden_layers",
@@ -36,9 +29,15 @@
             {
                 "name": "model.layers.${layer_index}.mlp.up_proj.weight"
             },
+            {
+                "name": "model.layers.${layer_index}.self_attn.q_norm.weight"
+            },
             {
                 "name": "model.layers.${layer_index}.self_attn.q_proj.weight"
             },
+           {
+                "name": "model.layers.${layer_index}.self_attn.k_norm.weight"
+            },
             {
                 "name": "model.layers.${layer_index}.self_attn.k_proj.weight"
             },

This is a hack, but it works fine for c4ai-command-r-plus self-merging.

softwareweaver

Jun 15, 2024

Thanks. I will try that. I was thinking of merging command-r with softwareweaver/Twilight-Miqu-146B

nitky changed discussion status to closed Jun 15, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment