Instructions to use MotherEarth/MotherEarth-1.0-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MotherEarth/MotherEarth-1.0-8B with Transformers:

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

pipe = pipeline("text-generation", model="MotherEarth/MotherEarth-1.0-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("MotherEarth/MotherEarth-1.0-8B")
model = AutoModelForMultimodalLM.from_pretrained("MotherEarth/MotherEarth-1.0-8B")
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 MotherEarth/MotherEarth-1.0-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MotherEarth/MotherEarth-1.0-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MotherEarth/MotherEarth-1.0-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MotherEarth/MotherEarth-1.0-8B

SGLang

How to use MotherEarth/MotherEarth-1.0-8B 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 "MotherEarth/MotherEarth-1.0-8B" \
    --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": "MotherEarth/MotherEarth-1.0-8B",
		"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 "MotherEarth/MotherEarth-1.0-8B" \
        --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": "MotherEarth/MotherEarth-1.0-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MotherEarth/MotherEarth-1.0-8B with Docker Model Runner:
```
docker model run hf.co/MotherEarth/MotherEarth-1.0-8B
```

MotherEarth commited on Sep 16, 2024

Commit

5b762a5

verified ·

1 Parent(s): f3d88b9

Upload folder using huggingface_hub

Browse files

Files changed (7) hide show

README.md +5 -5
config.json +1 -1
mergekit_config.yml +3 -3
model-00001-of-00004.safetensors +2 -2
model-00002-of-00004.safetensors +2 -2
model-00003-of-00004.safetensors +2 -2
model-00004-of-00004.safetensors +2 -2

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 base_model:
-- MotherEarth/linear_MotherEarth_1.0_slerp_storm_aflah
 - MotherEarth/MotherEarth_1.0
 library_name: transformers
 tags:
@@ -20,7 +20,7 @@ This model was merged using the SLERP merge method.
 ### Models Merged
 The following models were included in the merge:
-* [MotherEarth/linear_MotherEarth_1.0_slerp_storm_aflah](https://huggingface.co/MotherEarth/linear_MotherEarth_1.0_slerp_storm_aflah)
 * [MotherEarth/MotherEarth_1.0](https://huggingface.co/MotherEarth/MotherEarth_1.0)
 ### Configuration
@@ -30,11 +30,11 @@ The following YAML configuration was used to produce this model:
 ```yaml
 models:
   - model: MotherEarth/MotherEarth_1.0
-  - model: MotherEarth/linear_MotherEarth_1.0_slerp_storm_aflah
 merge_method: slerp
 base_model: MotherEarth/MotherEarth_1.0
-dtype: float16
 parameters:
-  t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
 ```

 ---
 base_model:
+- MotherEarth/slerp_MotherEarth-MothErarth_slerp_aflah-linear_strom
 - MotherEarth/MotherEarth_1.0
 library_name: transformers
 tags:
 ### Models Merged
 The following models were included in the merge:
+* [MotherEarth/slerp_MotherEarth-MothErarth_slerp_aflah-linear_strom](https://huggingface.co/MotherEarth/slerp_MotherEarth-MothErarth_slerp_aflah-linear_strom)
 * [MotherEarth/MotherEarth_1.0](https://huggingface.co/MotherEarth/MotherEarth_1.0)
 ### Configuration
 ```yaml
 models:
   - model: MotherEarth/MotherEarth_1.0
+  - model: MotherEarth/slerp_MotherEarth-MothErarth_slerp_aflah-linear_strom
 merge_method: slerp
 base_model: MotherEarth/MotherEarth_1.0
+dtype: bfloat16
 parameters:
+  t: [0.2, 0.4, 0.8, 0.4, 0.2] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
 ```

config.json CHANGED Viewed

@@ -22,7 +22,7 @@
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
   "transformers_version": "4.44.1",
   "use_cache": true,
   "vocab_size": 128256

   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.44.1",
   "use_cache": true,
   "vocab_size": 128256

mergekit_config.yml CHANGED Viewed

@@ -1,8 +1,8 @@
 models:
   - model: MotherEarth/MotherEarth_1.0
-  - model: MotherEarth/linear_MotherEarth_1.0_slerp_storm_aflah
 merge_method: slerp
 base_model: MotherEarth/MotherEarth_1.0
-dtype: float16
 parameters:
-  t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers

 models:
   - model: MotherEarth/MotherEarth_1.0
+  - model: MotherEarth/slerp_MotherEarth-MothErarth_slerp_aflah-linear_strom
 merge_method: slerp
 base_model: MotherEarth/MotherEarth_1.0
+dtype: bfloat16
 parameters:
+  t: [0.2, 0.4, 0.8, 0.4, 0.2] # V shaped curve: Hermes for input & output, WizardMath in the middle layers

model-00001-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a31e9bb9b04c2bf28f11487a3f02fd00d6dcbbb24605241e777d155e1acd59b5
-size 4953586328

 version https://git-lfs.github.com/spec/v1
+oid sha256:003e3b378aacff044f449f7e3a8c8ad1b220961c5c7f7a415e679b0f9aa5f5a8
+size 4953586384

model-00002-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20a4a2c10dee3cd4bd80b10299fe48b249e271eb0fd7d4f447f0ac35bafdaab6
-size 4999819232

 version https://git-lfs.github.com/spec/v1
+oid sha256:2960c39b03dd4921bb38644fd22380ce7d3cd0de2d2eed43f9a88e3a1d943f8e
+size 4999819336

model-00003-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff7346df3b8a73e36f5ab57fee434f46f422d3602e1662cbbd9f6d2c91b43e53
-size 4915916048

 version https://git-lfs.github.com/spec/v1
+oid sha256:ed26b733779f321b51f886c6aefe974822be22c489c15afd911702721b50b568
+size 4915916144

model-00004-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da1e9b79ac4033521f122bb42b77c455733082f41e675c17c6aa561f220f883d
-size 1191234448

 version https://git-lfs.github.com/spec/v1
+oid sha256:27edd6cc3f5e44c9181df24c2fa0ac642b862ddcd786af3d8c160dea4a6e94c8
+size 1191234472