| { |
| "architectures": [ |
| "MistralForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "dtype": "bfloat16", |
| "eos_token_id": 2, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "max_position_embeddings": 32768, |
| "model_type": "mistral", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "pad_token_id": 0, |
| "quantization_config": { |
| "bits": 8, |
| "checkpoint_format": "gptq", |
| "desc_act": false, |
| "dynamic": { |
| "+:.*\\.20\\..*": { |
| "bits": 4 |
| }, |
| "+:.*\\.23\\..*": { |
| "bits": 4 |
| }, |
| "+:.*\\.24\\..*": { |
| "bits": 4 |
| }, |
| "+:.*\\.25\\..*": { |
| "bits": 4 |
| }, |
| "+:.*\\.26\\..*": { |
| "bits": 4 |
| }, |
| "+:.*\\.27\\..*": { |
| "bits": 4 |
| }, |
| "+:.*\\.28\\..*": { |
| "bits": 4 |
| }, |
| "+:.*\\.29\\..*": { |
| "bits": 4 |
| } |
| }, |
| "format": "gptq", |
| "group_size": 128, |
| "lm_head": false, |
| "meta": { |
| "act_group_aware": true, |
| "auto_forward_data_parallel": true, |
| "damp_auto_increment": 0.01, |
| "damp_percent": 0.05, |
| "dense_vram_strategy": "exclusive", |
| "dense_vram_strategy_devices": null, |
| "fallback": { |
| "smooth": null, |
| "strategy": "rtn", |
| "threshold": "0.5%" |
| }, |
| "foem": null, |
| "gc_mode": "interval", |
| "gptaq": null, |
| "hessian": { |
| "chunk_bytes": null, |
| "chunk_size": null, |
| "staging_dtype": "float32" |
| }, |
| "mock_quantization": false, |
| "moe_vram_strategy": "exclusive", |
| "moe_vram_strategy_devices": null, |
| "mse": 0.0, |
| "offload_to_disk": true, |
| "offload_to_disk_path": "/tmp/gptqmodel_rlebkvo4", |
| "pack_impl": "cpu", |
| "quantizer": [ |
| "gptqmodel:7.0.0" |
| ], |
| "static_groups": false, |
| "true_sequential": true, |
| "uri": "https://github.com/modelcloud/gptqmodel", |
| "wait_for_submodule_finalizers": false |
| }, |
| "method": "gptq", |
| "pack_dtype": "int32", |
| "quant_method": "gptq", |
| "sym": true |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "rope_theta": 1000000.0, |
| "rope_type": "default" |
| }, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.8.1", |
| "use_cache": true, |
| "vocab_size": 32768 |
| } |
|
|
