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 3 days ago

Commit

df5a06b

verified ·

1 Parent(s): 4df46a4

chunk 600 (W2.8 cutover BASE): upload model.safetensors.index.json

Browse files

Files changed (1) hide show

model.safetensors.index.json +35 -35

model.safetensors.index.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 13754776586
   },
   "weight_map": {
     "tok_emb.weight": "model-00001-of-00003.safetensors",
@@ -160,17 +160,17 @@
     "blocks.17.attn.wq.weight": "model-00001-of-00003.safetensors",
     "blocks.17.attn.wk.weight": "model-00001-of-00003.safetensors",
     "blocks.17.attn.wv.weight": "model-00001-of-00003.safetensors",
-    "blocks.17.attn.wo.weight": "model-00001-of-00003.safetensors",
-    "blocks.17.ff.w1.weight": "model-00001-of-00003.safetensors",
-    "blocks.17.ff.w2.weight": "model-00001-of-00003.safetensors",
-    "blocks.17.ff.w3.weight": "model-00001-of-00003.safetensors",
-    "blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
-    "blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
-    "blocks.18.attn.wq.weight": "model-00001-of-00003.safetensors",
-    "blocks.18.attn.wk.weight": "model-00001-of-00003.safetensors",
-    "blocks.18.attn.wv.weight": "model-00001-of-00003.safetensors",
-    "blocks.18.attn.wo.weight": "model-00001-of-00003.safetensors",
-    "blocks.18.ff.w1.weight": "model-00001-of-00003.safetensors",
     "blocks.18.ff.w2.weight": "model-00002-of-00003.safetensors",
     "blocks.18.ff.w3.weight": "model-00002-of-00003.safetensors",
     "blocks.18.norm1.weight": "model-00002-of-00003.safetensors",
@@ -323,29 +323,29 @@
     "blocks.35.attn.wk.weight": "model-00002-of-00003.safetensors",
     "blocks.35.attn.wv.weight": "model-00002-of-00003.safetensors",
     "blocks.35.attn.wo.weight": "model-00002-of-00003.safetensors",
-    "blocks.35.ff.w1.weight": "model-00002-of-00003.safetensors",
-    "blocks.35.ff.w2.weight": "model-00002-of-00003.safetensors",
-    "blocks.35.ff.w3.weight": "model-00002-of-00003.safetensors",
-    "blocks.35.norm1.weight": "model-00002-of-00003.safetensors",
-    "blocks.35.norm2.weight": "model-00002-of-00003.safetensors",
-    "blocks.36.attn.wq.weight": "model-00002-of-00003.safetensors",
-    "blocks.36.attn.wk.weight": "model-00002-of-00003.safetensors",
-    "blocks.36.attn.wv.weight": "model-00002-of-00003.safetensors",
-    "blocks.36.attn.wo.weight": "model-00002-of-00003.safetensors",
-    "blocks.36.ff.w1.weight": "model-00002-of-00003.safetensors",
-    "blocks.36.ff.w2.weight": "model-00002-of-00003.safetensors",
-    "blocks.36.ff.w3.weight": "model-00002-of-00003.safetensors",
-    "blocks.36.norm1.weight": "model-00002-of-00003.safetensors",
-    "blocks.36.norm2.weight": "model-00002-of-00003.safetensors",
-    "blocks.37.attn.wq.weight": "model-00002-of-00003.safetensors",
-    "blocks.37.attn.wk.weight": "model-00002-of-00003.safetensors",
-    "blocks.37.attn.wv.weight": "model-00002-of-00003.safetensors",
-    "blocks.37.attn.wo.weight": "model-00002-of-00003.safetensors",
-    "blocks.37.ff.w1.weight": "model-00002-of-00003.safetensors",
-    "blocks.37.ff.w2.weight": "model-00002-of-00003.safetensors",
-    "blocks.37.ff.w3.weight": "model-00002-of-00003.safetensors",
-    "blocks.37.norm1.weight": "model-00002-of-00003.safetensors",
-    "blocks.37.norm2.weight": "model-00002-of-00003.safetensors",
     "blocks.38.attn.wq.weight": "model-00003-of-00003.safetensors",
     "blocks.38.attn.wk.weight": "model-00003-of-00003.safetensors",
     "blocks.38.attn.wv.weight": "model-00003-of-00003.safetensors",

 {
   "metadata": {
+    "total_size": 13754776394
   },
   "weight_map": {
     "tok_emb.weight": "model-00001-of-00003.safetensors",
     "blocks.17.attn.wq.weight": "model-00001-of-00003.safetensors",
     "blocks.17.attn.wk.weight": "model-00001-of-00003.safetensors",
     "blocks.17.attn.wv.weight": "model-00001-of-00003.safetensors",
+    "blocks.17.attn.wo.weight": "model-00002-of-00003.safetensors",
+    "blocks.17.ff.w1.weight": "model-00002-of-00003.safetensors",
+    "blocks.17.ff.w2.weight": "model-00002-of-00003.safetensors",
+    "blocks.17.ff.w3.weight": "model-00002-of-00003.safetensors",
+    "blocks.17.norm1.weight": "model-00002-of-00003.safetensors",
+    "blocks.17.norm2.weight": "model-00002-of-00003.safetensors",
+    "blocks.18.attn.wq.weight": "model-00002-of-00003.safetensors",
+    "blocks.18.attn.wk.weight": "model-00002-of-00003.safetensors",
+    "blocks.18.attn.wv.weight": "model-00002-of-00003.safetensors",
+    "blocks.18.attn.wo.weight": "model-00002-of-00003.safetensors",
+    "blocks.18.ff.w1.weight": "model-00002-of-00003.safetensors",
     "blocks.18.ff.w2.weight": "model-00002-of-00003.safetensors",
     "blocks.18.ff.w3.weight": "model-00002-of-00003.safetensors",
     "blocks.18.norm1.weight": "model-00002-of-00003.safetensors",
     "blocks.35.attn.wk.weight": "model-00002-of-00003.safetensors",
     "blocks.35.attn.wv.weight": "model-00002-of-00003.safetensors",
     "blocks.35.attn.wo.weight": "model-00002-of-00003.safetensors",
+    "blocks.35.ff.w1.weight": "model-00003-of-00003.safetensors",
+    "blocks.35.ff.w2.weight": "model-00003-of-00003.safetensors",
+    "blocks.35.ff.w3.weight": "model-00003-of-00003.safetensors",
+    "blocks.35.norm1.weight": "model-00003-of-00003.safetensors",
+    "blocks.35.norm2.weight": "model-00003-of-00003.safetensors",
+    "blocks.36.attn.wq.weight": "model-00003-of-00003.safetensors",
+    "blocks.36.attn.wk.weight": "model-00003-of-00003.safetensors",
+    "blocks.36.attn.wv.weight": "model-00003-of-00003.safetensors",
+    "blocks.36.attn.wo.weight": "model-00003-of-00003.safetensors",
+    "blocks.36.ff.w1.weight": "model-00003-of-00003.safetensors",
+    "blocks.36.ff.w2.weight": "model-00003-of-00003.safetensors",
+    "blocks.36.ff.w3.weight": "model-00003-of-00003.safetensors",
+    "blocks.36.norm1.weight": "model-00003-of-00003.safetensors",
+    "blocks.36.norm2.weight": "model-00003-of-00003.safetensors",
+    "blocks.37.attn.wq.weight": "model-00003-of-00003.safetensors",
+    "blocks.37.attn.wk.weight": "model-00003-of-00003.safetensors",
+    "blocks.37.attn.wv.weight": "model-00003-of-00003.safetensors",
+    "blocks.37.attn.wo.weight": "model-00003-of-00003.safetensors",
+    "blocks.37.ff.w1.weight": "model-00003-of-00003.safetensors",
+    "blocks.37.ff.w2.weight": "model-00003-of-00003.safetensors",
+    "blocks.37.ff.w3.weight": "model-00003-of-00003.safetensors",
+    "blocks.37.norm1.weight": "model-00003-of-00003.safetensors",
+    "blocks.37.norm2.weight": "model-00003-of-00003.safetensors",
     "blocks.38.attn.wq.weight": "model-00003-of-00003.safetensors",
     "blocks.38.attn.wk.weight": "model-00003-of-00003.safetensors",
     "blocks.38.attn.wv.weight": "model-00003-of-00003.safetensors",