Sandiago21's picture
add fine-tuned model trained on multilingual conversations based on decapoda-research/llama-13b-hf model
f8de50b
raw
history blame
981 Bytes
{
"_name_or_path": "../../llama-13b-hf-prompt-answering/decapoda-research/llama-13b-hf/",
"architectures": [
"LLaMAForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 1,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 2048,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"pad_token_id": -1,
"quantization_config": {
"bnb_4bit_compute_dtype": "float32",
"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
},
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.30.0.dev0",
"use_cache": false,
"vocab_size": 32000
}