sharpenb's picture
8815971022887006734b0ff8e9e45f5045a7fed611ac2e9f67be6a7940d936c0
5e42191 verified
raw
history blame
1.69 kB
{
"_name_or_path": "/ceph/hdd/staff/charpent/.cache/models9r4ipwkwo6dk0y7v",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"custom_pipelines": {
"text-generation": {
"impl": "instruct_pipeline.InstructionTextGenerationPipeline",
"pt": "AutoModelForCausalLM",
"tf": "TFAutoModelForCausalLM"
}
},
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 1600,
"n_head": 25,
"n_inner": null,
"n_layer": 48,
"n_positions": 1024,
"output_past": true,
"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"
},
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"torch_dtype": "float16",
"transformers_version": "4.40.0",
"use_cache": false,
"vocab_size": 50260
}