| { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5", |
| "architectures": [ |
| "GPTNeoXForCausalLM" |
| ], |
| "attention_bias": true, |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "classifier_dropout": 0.1, |
| "eos_token_id": 0, |
| "hidden_act": "gelu", |
| "hidden_dropout": 0.0, |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 20480, |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 2048, |
| "model_type": "gpt_neox", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 36, |
| "partial_rotary_factor": 0.25, |
| "quantization_config": { |
| "_load_in_4bit": true, |
| "_load_in_8bit": false, |
| "bnb_4bit_compute_dtype": "bfloat16", |
| "bnb_4bit_quant_storage": "bfloat16", |
| "bnb_4bit_quant_type": "nf4", |
| "bnb_4bit_use_double_quant": true, |
| "llm_int8_enable_fp32_cpu_offload": false, |
| "llm_int8_has_fp16_weight": false, |
| "llm_int8_skip_modules": null, |
| "llm_int8_threshold": 6.0, |
| "load_in_4bit": true, |
| "load_in_8bit": false, |
| "quant_method": "bitsandbytes" |
| }, |
| "rope_scaling": null, |
| "rope_theta": 10000, |
| "rotary_emb_base": 10000, |
| "rotary_pct": 0.25, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.46.0", |
| "use_cache": false, |
| "use_parallel_residual": true, |
| "vocab_size": 50288 |
| } |
|
|
