qwopqwop's picture
Update max_position_embeddings to 128k context size instead of 32k(https://huggingface.co/mistralai/Mistral-Large-Instruct-2407/commit/5c9ce5b5f7a7ad62d03e8c66c719b66d586de26b)
aaf1973 verified
raw
history blame
855 Bytes
{
"_name_or_path": "mistralai/Mistral-Large-Instruct-2407",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 12288,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 131072,
"model_type": "mistral",
"num_attention_heads": 96,
"num_hidden_layers": 88,
"num_key_value_heads": 8,
"quantization_config": {
"bits": 4,
"group_size": 128,
"modules_to_not_convert": null,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.43.2",
"use_cache": true,
"vocab_size": 32768
}