sharpenb's picture
d771cc3a9729bb74cf481771c820b4a2ae255e53aa8dabdeaa42d963f06b4509
4e9aae9 verified
raw
history blame
1.31 kB
{
"_name_or_path": "/ceph/hdd/staff/charpent/.cache/modelsdcj1aey5gp27yi5u",
"architectures": [
"StableLmForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"eos_token_id": 0,
"hidden_act": "silu",
"hidden_dropout": 0.0,
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 6912,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 4096,
"model_type": "stablelm",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"partial_rotary_factor": 0.25,
"qk_layernorm": false,
"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"
},
"rope_scaling": null,
"rope_theta": 10000,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.42.4",
"use_cache": true,
"use_parallel_residual": false,
"use_qkv_bias": false,
"vocab_size": 50304
}