| { |
| "_name_or_path": "./tmp_autoround_gptq", |
| "architectures": [ |
| "InternLM3ForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_internlm3.InternLM3Config", |
| "AutoModel": "modeling_internlm3.InternLM3Model", |
| "AutoModelForCausalLM": "modeling_internlm3.InternLM3ForCausalLM" |
| }, |
| "bias": false, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 10240, |
| "max_position_embeddings": 32768, |
| "model_type": "internlm3", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 48, |
| "num_key_value_heads": 2, |
| "pad_token_id": 2, |
| "qkv_bias": false, |
| "quantization_config": { |
| "batch_size": 4, |
| "bits": 4, |
| "block_name_to_quantize": null, |
| "cache_block_outputs": true, |
| "damp_percent": 0.01, |
| "dataset": null, |
| "desc_act": false, |
| "exllama_config": { |
| "version": 1 |
| }, |
| "group_size": 128, |
| "max_input_length": null, |
| "model_seqlen": null, |
| "module_name_preceding_first_block": null, |
| "modules_in_block_to_quantize": null, |
| "pad_token_id": null, |
| "quant_method": "gptq", |
| "sym": true, |
| "tokenizer": null, |
| "true_sequential": false, |
| "use_cuda_fp16": false, |
| "use_exllama": true |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "factor": 6.0, |
| "rope_type": "dynamic" |
| }, |
| "rope_theta": 50000000, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.48.0", |
| "use_cache": true, |
| "vocab_size": 128512 |
| } |
|
|
