47 lines
1.2 KiB
JSON
47 lines
1.2 KiB
JSON
|
{
|
||
|
|
"_name_or_path": "lakkeo/stable-cypher-instruct-3b",
|
||
|
|
"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": 16384,
|
||
|
|
"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": 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"
|
||
|
|
},
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 1000000,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "float32",
|
||
|
|
"transformers_version": "4.41.2",
|
||
|
|
"use_cache": false,
|
||
|
|
"use_parallel_residual": false,
|
||
|
|
"use_qkv_bias": false,
|
||
|
|
"vocab_size": 50304
|
||
|
|
}
|