mlconvexai's picture
Upload model
45bae7d verified
raw
history blame
1.83 kB
{
"_name_or_path": "core42/jais-13b-chat",
"activation_function": "swiglu",
"architectures": [
"JAISLMHeadModel"
],
"attn_pdrop": 0.0,
"auto_map": {
"AutoConfig": "core42/jais-13b-chat--configuration_jais.JAISConfig",
"AutoModel": "core42/jais-13b-chat--modeling_jais.JAISModel",
"AutoModelForCausalLM": "core42/jais-13b-chat--modeling_jais.JAISLMHeadModel",
"AutoModelForQuestionAnswering": "core42/jais-13b-chat--modeling_jais.JAISForQuestionAnswering",
"AutoModelForSequenceClassification": "core42/jais-13b-chat--modeling_jais.JAISForSequenceClassification",
"AutoModelForTokenClassification": "core42/jais-13b-chat--modeling_jais.JAISForTokenClassification"
},
"bos_token_id": 0,
"embd_pdrop": 0.0,
"embeddings_scale": 14.6,
"eos_token_id": 0,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "jais",
"n_embd": 5120,
"n_head": 40,
"n_inner": 13653,
"n_layer": 40,
"n_positions": 2048,
"pad_token_id": 0,
"position_embedding_type": "alibi",
"quantization_config": {
"_load_in_4bit": false,
"_load_in_8bit": true,
"bnb_4bit_compute_dtype": "float32",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "fp4",
"bnb_4bit_use_double_quant": false,
"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": false,
"load_in_8bit": true,
"quant_method": "bitsandbytes"
},
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.0,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"scale_qk_dot_by_d": true,
"torch_dtype": "float16",
"transformers_version": "4.44.0",
"use_cache": true,
"vocab_size": 84992,
"width_scale": 0.11100000000000002
}