| { |
| "_name_or_path": "/root/.cache/huggingface/hub/models--bigcode--starcoder2-7b/snapshots/bb9afde76d7945da5745592525db122d4d729eb1", |
| "activation_function": "gelu", |
| "architectures": [ |
| "Starcoder2ForCausalLM" |
| ], |
| "attention_dropout": 0.1, |
| "attention_softmax_in_fp32": true, |
| "bos_token_id": 0, |
| "embedding_dropout": 0.1, |
| "eos_token_id": 0, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 4608, |
| "initializer_range": 0.018042, |
| "intermediate_size": 18432, |
| "layer_norm_epsilon": 1e-05, |
| "max_position_embeddings": 16384, |
| "mlp_type": "default", |
| "model_type": "starcoder2", |
| "norm_epsilon": 1e-05, |
| "norm_type": "layer_norm", |
| "num_attention_heads": 36, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 4, |
| "residual_dropout": 0.1, |
| "rope_theta": 1000000, |
| "scale_attention_softmax_in_fp32": true, |
| "scale_attn_weights": true, |
| "sliding_window": 4096, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.43.3", |
| "use_bias": true, |
| "use_cache": true, |
| "vocab_size": 49152, |
| "quantization_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": 1.4228628352040205, |
| "ignore": [ |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "frozen", |
| "sparsity_config": { |
| "format": "dense", |
| "global_sparsity": 1.3962297793225527, |
| "registry_requires_subclass": false, |
| "sparsity_structure": "unstructured" |
| } |
| } |
| } |
