interstellarninja's picture
Training in progress, step 100
89012d4 verified
{
"_name_or_path": "/home/interstellarninja/ai_projects/axolotl/stablelm-1_6b-tool-calling-1/merged",
"architectures": [
"StableLMEpochForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_stablelm_epoch.StableLMEpochConfig",
"AutoModelForCausalLM": "modeling_stablelm_epoch.StableLMEpochForCausalLM"
},
"bos_token_id": 100257,
"eos_token_id": 100257,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 4096,
"model_type": "stablelm_epoch",
"norm_eps": 1e-05,
"num_attention_heads": 32,
"num_heads": 32,
"num_hidden_layers": 24,
"num_key_value_heads": 32,
"quantization_config": {
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true,
"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": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"rope_pct": 0.25,
"rope_theta": 10000,
"rotary_scaling_factor": 1.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.0.dev0",
"use_cache": false,
"use_qkv_bias": true,
"vocab_size": 100352
}