Instructions to use codewithdark/latent-recurrent-depth-lm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codewithdark/latent-recurrent-depth-lm with Transformers:

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

pipe = pipeline("text-generation", model="codewithdark/latent-recurrent-depth-lm", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("codewithdark/latent-recurrent-depth-lm", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codewithdark/latent-recurrent-depth-lm with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/codewithdark/latent-recurrent-depth-lm

SGLang

How to use codewithdark/latent-recurrent-depth-lm 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 "codewithdark/latent-recurrent-depth-lm" \
    --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": "codewithdark/latent-recurrent-depth-lm",
		"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 "codewithdark/latent-recurrent-depth-lm" \
        --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": "codewithdark/latent-recurrent-depth-lm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use codewithdark/latent-recurrent-depth-lm with Docker Model Runner:
```
docker model run hf.co/codewithdark/latent-recurrent-depth-lm
```

codewithdark commited on Feb 24, 2025

Commit

2ae649f

1 Parent(s): 7191f6d

Initial model and tokenizer commit

Browse files

Files changed (4) hide show

config.json +1 -1
generation_config.json +1 -1
model.safetensors +1 -1
tokenizer.json +2 -2

config.json CHANGED Viewed

@@ -7,6 +7,6 @@
   "model_type": "latent_recurrent_depth",
   "num_heads": 12,
   "torch_dtype": "float32",
-  "transformers_version": "4.48.3",
   "vocab_size": 50257
 }

   "model_type": "latent_recurrent_depth",
   "num_heads": 12,
   "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
   "vocab_size": 50257
 }

generation_config.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
   "_from_model_config": true,
-  "transformers_version": "4.48.3"
 }

 {
   "_from_model_config": true,
+  "transformers_version": "4.47.0"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148289c329ecae9a79fc14092bc811e75b3f5f20bd546dc36e19b63588b15c44
 size 371201724

 version https://git-lfs.github.com/spec/v1
+oid sha256:df4f0cbeb4e6d14b9e67cd858f4965ab91c60cea1a1236a4667406e5b9317bae
 size 371201724

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b15c1a97a786165f191fc6eacc0c4332fc7bc57202c48724c3ba18fecd080364
-size 322560

 version https://git-lfs.github.com/spec/v1
+oid sha256:ace89058422d73b0f7e9f261db7a46e407650849dbf7e0f1aeee784cf04a2c3f
+size 3383360