sharpenb's picture
0b08c417d663623f8f777a1e2d5a24b8ecaaa185dccad5bda69d9d71a547f9f9
620375d verified
raw
history blame
1.47 kB
{
"_name_or_path": "/ceph/hdd/staff/charpent/.cache/models07rrebd6rr1w8jk7",
"activation_function": "gelu",
"architectures": [
"Starcoder2ForCausalLM"
],
"attention_dropout": 0.0,
"attention_softmax_in_fp32": true,
"bos_token_id": 0,
"embedding_dropout": 0.0,
"eos_token_id": 0,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 4608,
"initializer_range": 0.018042,
"intermediate_size": 18432,
"layer_norm_epsilon": 1e-05,
"max_position_embeddings": 16384,
"mlp_type": "default",
"model_type": "starcoder2",
"norm_epsilon": 1e-05,
"norm_type": "layer_norm",
"num_attention_heads": 36,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"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": [
"lm_head"
],
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"residual_dropout": 0.0,
"rope_theta": 1000000,
"scale_attention_softmax_in_fp32": true,
"scale_attn_weights": true,
"sliding_window": 4096,
"torch_dtype": "float16",
"transformers_version": "4.40.0",
"use_bias": true,
"use_cache": false,
"vocab_size": 49154
}