Text Generation
Transformers.js
ONNX
llama
webgpu
q4f16
gptq
tool-calling
experimental
conversational
Instructions to use webbrain-one/webbrain-compass-tiny-v2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use webbrain-one/webbrain-compass-tiny-v2.1 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'webbrain-one/webbrain-compass-tiny-v2.1');
| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "dtype": "bfloat16", | |
| "eos_token_id": [ | |
| 1, | |
| 130073 | |
| ], | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 42, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 1, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "rope_theta": 5000000, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.16.1", | |
| "use_cache": true, | |
| "vocab_size": 130560, | |
| "transformers.js_config": { | |
| "kv_cache_dtype": { | |
| "q4f16": "float16" | |
| }, | |
| "use_external_data_format": { | |
| "model_q4f16.onnx": 2 | |
| } | |
| } | |
| } | |