sharpenb's picture
Upload folder using huggingface_hub (#4)
76aa6ed verified
{
"_name_or_path": "/covalent/.cache/models/tmpgdzulhq_c37441dg",
"architectures": [
"KPhi3ForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_kphi3.KPhi3Config",
"AutoModelForCausalLM": "schuler/experimental-JP47D20--modeling_kphi3.KPhi3ForCausalLM"
},
"bos_token_id": 1,
"embd_pdrop": 0.0,
"embed_size": 1024,
"eos_token_id": 2,
"ffn_dim": 1024,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"max_position_embeddings": 131072,
"min_channels_per_group": 256,
"model_type": "kphi3",
"num_attention_heads": 16,
"num_hidden_layers": 32,
"num_key_value_heads": 16,
"original_max_position_embeddings": 4096,
"pad_token_id": 32000,
"quantization_config": {
"_load_in_4bit": false,
"_load_in_8bit": true,
"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": false,
"load_in_8bit": true,
"quant_method": "bitsandbytes"
},
"resid_pdrop": 0.0,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.46.2",
"use_cache": true,
"vocab_size": 32064,
"api_key": null
}