| { |
| "_name_or_path": "/home/linghao/.cache/huggingface/hub/models--bigcode--starcoder2-3b/snapshots/733247c55e3f73af49ce8e9c7949bf14af205928", |
| "architectures": [ |
| "Starcoder2ForCausalLM" |
| ], |
| "attention_dropout": 0.1, |
| "bos_token_id": 0, |
| "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": "float16", |
| "transformers_version": "4.44.0.dev0", |
| "use_bias": true, |
| "use_cache": true, |
| "vocab_size": 49152, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "input_activations": { |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": "minmax", |
| "observer_kwargs": {}, |
| "strategy": "tensor", |
| "symmetric": true, |
| "type": "float" |
| }, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": "minmax", |
| "observer_kwargs": {}, |
| "strategy": "tensor", |
| "symmetric": true, |
| "type": "float" |
| } |
| } |
| }, |
| "format": "naive-quantized", |
| "global_compression_ratio": 1.4225351755647873, |
| "ignore": [ |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "frozen" |
| } |
| } |
