| { |
| "activation_function": "gelu", |
| "architectures": [ |
| "GPTBigCodeForCausalLM" |
| ], |
| "attention_softmax_in_fp32": true, |
| "attn_pdrop": 0.1, |
| "bos_token_id": 0, |
| "embd_pdrop": 0.1, |
| "eos_token_id": 0, |
| "initializer_range": 0.02, |
| "layer_norm_epsilon": 1e-05, |
| "model_type": "gpt_bigcode", |
| "multi_query": true, |
| "n_embd": 6144, |
| "n_head": 48, |
| "n_inner": 24576, |
| "n_layer": 52, |
| "n_positions": 8192, |
| "pad_token_id": 0, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "input_activations": null, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 128, |
| "num_bits": 4, |
| "observer": "minmax", |
| "observer_kwargs": {}, |
| "strategy": "group", |
| "symmetric": true, |
| "type": "int" |
| } |
| } |
| }, |
| "format": "pack-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed" |
| }, |
| "resid_pdrop": 0.1, |
| "scale_attention_softmax_in_fp32": true, |
| "scale_attn_weights": true, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.3", |
| "use_cache": false, |
| "vocab_size": 49152 |
| } |
