| { | |
| "_name_or_path": "/root/.cache/huggingface/hub/models--bigcode--starcoder2-3b/snapshots/733247c55e3f73af49ce8e9c7949bf14af205928", | |
| "architectures": [ | |
| "Starcoder2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 0, | |
| "compression_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "input_activations": null, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": "minmax", | |
| "observer_kwargs": {}, | |
| "strategy": "channel", | |
| "symmetric": true, | |
| "type": "int" | |
| } | |
| } | |
| }, | |
| "format": "pack-quantized", | |
| "global_compression_ratio": 1.803492483621931, | |
| "ignore": [ | |
| "lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "frozen", | |
| "sparsity_config": { | |
| "format": "dense", | |
| "global_sparsity": 1.333353131567116, | |
| "registry_requires_subclass": false, | |
| "sparsity_structure": "unstructured" | |
| } | |
| }, | |
| "embedding_dropout": 0.1, | |
| "eos_token_id": 0, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 3072, | |
| "initializer_range": 0.018042, | |
| "intermediate_size": 12288, | |
| "max_position_embeddings": 16384, | |
| "mlp_type": "default", | |
| "model_type": "starcoder2", | |
| "norm_epsilon": 1e-05, | |
| "norm_type": "layer_norm", | |
| "num_attention_heads": 24, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 2, | |
| "residual_dropout": 0.1, | |
| "rope_theta": 999999.4420358813, | |
| "sliding_window": 4096, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.43.3", | |
| "use_bias": true, | |
| "use_cache": true, | |
| "vocab_size": 49152 | |
| } |