Instructions to use mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch with Transformers:

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

pipe = pipeline("text-generation", model="mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch

SGLang

How to use mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch 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 "mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch" \
    --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": "mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch",
		"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 "mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch" \
        --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": "mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch with Docker Model Runner:
```
docker model run hf.co/mlnomad/yatnmn-softplus-d12-chinchilla-261M-pytorch
```

mlnomad commited on Apr 29

Commit

4dd4b4f

verified ·

1 Parent(s): 8a6af7d

Fix: lazy non-persistent RoPE buffers — HF from_pretrained's meta-init was leaving persistent rope_cos/rope_sin uninitialised, producing NaN logits. Buffers are now computed on first forward.

Browse files

Files changed (1) hide show

yatnmn_gpt.py +2 -2

yatnmn_gpt.py CHANGED Viewed

@@ -26,12 +26,12 @@ import torch.nn as nn
 import torch.nn.functional as F
 try:
-    from torch_port.torch_gpt import (
         rms_norm, precompute_rotary_embeddings, apply_rotary_emb,
         has_ve, compute_window_sizes,
     )
 except ImportError:
-    from torch_gpt import (  # type: ignore
         rms_norm, precompute_rotary_embeddings, apply_rotary_emb,
         has_ve, compute_window_sizes,
     )

 import torch.nn.functional as F
 try:
+    from .torch_gpt import (
         rms_norm, precompute_rotary_embeddings, apply_rotary_emb,
         has_ve, compute_window_sizes,
     )
 except ImportError:
+    from torch_port.torch_gpt import (
         rms_norm, precompute_rotary_embeddings, apply_rotary_emb,
         has_ve, compute_window_sizes,
     )