Text Generation
Transformers
Safetensors
ncp_smol
next-concept-prediction
conceptlm
causal-lm
smollm2
tessera
custom_code
Instructions to use yava-code/Tessera-135M-Gate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yava-code/Tessera-135M-Gate with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="yava-code/Tessera-135M-Gate", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("yava-code/Tessera-135M-Gate", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use yava-code/Tessera-135M-Gate with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "yava-code/Tessera-135M-Gate" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yava-code/Tessera-135M-Gate", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/yava-code/Tessera-135M-Gate
- SGLang
How to use yava-code/Tessera-135M-Gate 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 "yava-code/Tessera-135M-Gate" \ --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": "yava-code/Tessera-135M-Gate", "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 "yava-code/Tessera-135M-Gate" \ --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": "yava-code/Tessera-135M-Gate", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use yava-code/Tessera-135M-Gate with Docker Model Runner:
docker model run hf.co/yava-code/Tessera-135M-Gate
Download config.json from yava-code/Tessera-135M-Gate: direct link, hf CLI and curl.
- Browser
- Download file 3.1 kB
-
https://huggingface.co/yava-code/Tessera-135M-Gate/resolve/main/config.json
- Command line
-
hf download hf://yava-code/Tessera-135M-Gate/config.json
-
curl -L -o config.json https://huggingface.co/yava-code/Tessera-135M-Gate/resolve/main/config.json
3.1 kB
| { | |
| "architectures": [ | |
| "NcpSmolForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration.NcpSmolConfig", | |
| "AutoModelForCausalLM": "modeling.NcpSmolForCausalLM" | |
| }, | |
| "backbone_config": { | |
| "_name_or_path": "HuggingFaceTB/SmolLM2-135M", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_implementation": null, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 0, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dtype": "float32", | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 0, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 576, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.041666666666666664, | |
| "intermediate_size": 1536, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "is_llama_config": true, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 8192, | |
| "min_length": 0, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 9, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 3, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "pretraining_tp": 1, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-05, | |
| "rope_interleaved": false, | |
| "rope_scaling": null, | |
| "rope_theta": 100000, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "transformers_version": "4.57.6", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "vocab_size": 49152 | |
| }, | |
| "base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M", | |
| "base_model_revision": "93efa2f097d58c2a74874c7e644dbc9b0cee75a2", | |
| "chunk_size": 4, | |
| "codebook_size": 64, | |
| "concept_layers": 2, | |
| "dtype": "float32", | |
| "hidden_size": 576, | |
| "insert_layer": 1, | |
| "model_type": "ncp_smol", | |
| "ncp_target": "continuous", | |
| "ncp_weight": 1.0, | |
| "num_attention_heads": 9, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 3, | |
| "segments": 9, | |
| "transformers_version": "4.57.6", | |
| "use_cache": false, | |
| "vocab_size": 49152, | |
| "vq_weight": 1.0 | |
| } | |