Instructions to use MediaStreamAI/MOTHER_CORE_V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MediaStreamAI/MOTHER_CORE_V2 with Transformers:

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

pipe = pipeline("text-generation", model="MediaStreamAI/MOTHER_CORE_V2", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("MediaStreamAI/MOTHER_CORE_V2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MediaStreamAI/MOTHER_CORE_V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MediaStreamAI/MOTHER_CORE_V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MediaStreamAI/MOTHER_CORE_V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MediaStreamAI/MOTHER_CORE_V2

SGLang

How to use MediaStreamAI/MOTHER_CORE_V2 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 "MediaStreamAI/MOTHER_CORE_V2" \
    --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": "MediaStreamAI/MOTHER_CORE_V2",
		"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 "MediaStreamAI/MOTHER_CORE_V2" \
        --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": "MediaStreamAI/MOTHER_CORE_V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MediaStreamAI/MOTHER_CORE_V2 with Docker Model Runner:
```
docker model run hf.co/MediaStreamAI/MOTHER_CORE_V2
```

MediaStreamAI commited on 13 days ago

Commit

475fa9f

verified ·

1 Parent(s): 23fb721

chunk 600 (W2.8 cutover BASE): upload config.json

Browse files

Files changed (1) hide show

config.json +20 -17

config.json CHANGED Viewed

@@ -1,23 +1,26 @@
 {
-  "vocab_size": 50258,
-  "dim": 3072,
-  "n_layers": 48,
-  "n_heads": 24,
-  "n_kv_heads": 6,
-  "ff_mult": 4.0,
-  "max_seq_len": 4096,
-  "rope_theta": 10000.0,
-  "rms_norm_eps": 1e-05,
-  "tie_embeddings": false,
-  "dropout": 0.0,
-  "use_flash_if_available": true,
-  "model_type": "mother_core",
   "architectures": [
     "MotherCoreModel"
   ],
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.0",
-  "_msai_chunk": 450,
-  "_msai_training_stage": "W2.7",
-  "_msai_total_params_b": 6.877
 }

 {
   "architectures": [
     "MotherCoreModel"
   ],
+  "model_type": "mother_core",
   "torch_dtype": "bfloat16",
+  "vocab_size": 50258,
+  "hidden_size": 3072,
+  "num_hidden_layers": 48,
+  "num_attention_heads": 24,
+  "num_key_value_heads": 6,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 4096,
+  "rope_theta": 10000.0,
+  "rms_norm_eps": 1e-05,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "_msai_chunk": 600,
+  "_msai_corpus": "mother_core_w27_base.jsonl",
+  "_msai_weights": "MOTHER CORE BASE \u2014 chunk 600 frozen 2026-05-14",
+  "_msai_eval_score": "49/105 (47%)",
+  "_msai_source_sha256": "0b1ef35ec60af4a7ad0648498de8526cb775a19501dda94dfbda1713e0475b60"
 }