FlexingD's picture
Upload MistralForCausalLM
986d5fe
raw
history blame
No virus
1.36 kB
{
"_name_or_path": "NousResearch/Yarn-Mistral-7b-64k",
"architectures": [
"MistralForCausalLM"
],
"auto_map": {
"AutoConfig": "NousResearch/Yarn-Mistral-7b-64k--configuration_mistral.MistralConfig",
"AutoModelForCausalLM": "NousResearch/Yarn-Mistral-7b-64k--modeling_mistral_yarn.MistralForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"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,
"quant_method": "bitsandbytes"
},
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"finetuned": true,
"original_max_position_embeddings": 8192,
"type": "yarn"
},
"rope_theta": 10000.0,
"sliding_window": 65536,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.36.0.dev0",
"use_cache": true,
"vocab_size": 32000
}