Text Generation
Transformers
Safetensors
English
nanochat_gpt
base-model
pretraining
research
nanochat
scaling-ladder
custom_code
Instructions to use jkminder/d26_973m_seed2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jkminder/d26_973m_seed2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jkminder/d26_973m_seed2", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("jkminder/d26_973m_seed2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jkminder/d26_973m_seed2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jkminder/d26_973m_seed2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jkminder/d26_973m_seed2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jkminder/d26_973m_seed2
- SGLang
How to use jkminder/d26_973m_seed2 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 "jkminder/d26_973m_seed2" \ --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": "jkminder/d26_973m_seed2", "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 "jkminder/d26_973m_seed2" \ --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": "jkminder/d26_973m_seed2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jkminder/d26_973m_seed2 with Docker Model Runner:
docker model run hf.co/jkminder/d26_973m_seed2
Download config.json from jkminder/d26_973m_seed2: direct link, hf CLI and curl.
- Browser
- Download file 977 Bytes
-
https://huggingface.co/jkminder/d26_973m_seed2/resolve/main/config.json
- Command line
-
hf download hf://jkminder/d26_973m_seed2/config.json
-
curl -L -o config.json https://huggingface.co/jkminder/d26_973m_seed2/resolve/main/config.json
977 Bytes
| { | |
| "architectures": [ | |
| "NanochatGPTForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_nanochat_gpt.NanochatGPTConfig", | |
| "AutoModel": "modeling_nanochat_gpt.NanochatGPTModel", | |
| "AutoModelForCausalLM": "modeling_nanochat_gpt.NanochatGPTForCausalLM" | |
| }, | |
| "backout_layer": null, | |
| "bos_token_id": 32759, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 32759, | |
| "final_logit_softcapping": 15.0, | |
| "hidden_size": 1664, | |
| "intermediate_size": 6656, | |
| "logit_softcap": 15.0, | |
| "max_position_embeddings": 2048, | |
| "model_type": "nanochat_gpt", | |
| "num_attention_heads": 13, | |
| "num_hidden_layers": 26, | |
| "num_key_value_heads": 13, | |
| "qk_sharpen_scale": null, | |
| "rope_theta": 100000.0, | |
| "smear_gate_channels": 24, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.14.1", | |
| "use_resid_lambdas": false, | |
| "use_smear": false, | |
| "use_x0_lambdas": false, | |
| "value_embedding_layers": [], | |
| "ve_gate_channels": 12, | |
| "vocab_size": 32768, | |
| "window_pattern": "L" | |
| } | |