Instructions to use recursive-models/recursive1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use recursive-models/recursive1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="recursive-models/recursive1")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("recursive-models/recursive1", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use recursive-models/recursive1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "recursive-models/recursive1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "recursive-models/recursive1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/recursive-models/recursive1
- SGLang
How to use recursive-models/recursive1 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 "recursive-models/recursive1" \ --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": "recursive-models/recursive1", "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 "recursive-models/recursive1" \ --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": "recursive-models/recursive1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use recursive-models/recursive1 with Docker Model Runner:
docker model run hf.co/recursive-models/recursive1
Upload TRMForCausalLM
Browse files- config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -26,7 +26,7 @@
|
|
| 26 |
"name": "recursive_reasoning.trm@TinyRecursiveModel",
|
| 27 |
"no_ACT_continue": true,
|
| 28 |
"num_heads": 8,
|
| 29 |
-
"num_layers":
|
| 30 |
"num_puzzle_identifiers": 1,
|
| 31 |
"pos_encodings": "rope",
|
| 32 |
"pretrained_embeddings_model": "Alibaba-NLP/gte-modernbert-base",
|
|
|
|
| 26 |
"name": "recursive_reasoning.trm@TinyRecursiveModel",
|
| 27 |
"no_ACT_continue": true,
|
| 28 |
"num_heads": 8,
|
| 29 |
+
"num_layers": 4,
|
| 30 |
"num_puzzle_identifiers": 1,
|
| 31 |
"pos_encodings": "rope",
|
| 32 |
"pretrained_embeddings_model": "Alibaba-NLP/gte-modernbert-base",
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf1b29f3e306475a0f20b9ea682611acabb21f017ce4e20fc4e348162d9ed862
|
| 3 |
+
size 422719008
|