File size: 1,331 Bytes
ceeae43 9fe71fc ceeae43 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
{
"_name_or_path": "shuyuej/Command-R-Plus-GPTQ",
"architectures": [
"CohereForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 5,
"eos_token_id": 255001,
"hidden_act": "silu",
"hidden_size": 12288,
"initializer_range": 0.02,
"intermediate_size": 33792,
"layer_norm_eps": 1e-05,
"logit_scale": 0.8333333333333334,
"max_position_embeddings": 8192,
"model_max_length": 131072,
"model_type": "cohere",
"num_attention_heads": 96,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"pad_token_id": 0,
"quantization_config": {
"batch_size": 1,
"bits": 4,
"block_name_to_quantize": null,
"cache_block_outputs": true,
"damp_percent": 0.1,
"dataset": null,
"desc_act": false,
"exllama_config": {
"version": 1
},
"group_size": 128,
"max_input_length": null,
"model_seqlen": null,
"module_name_preceding_first_block": null,
"modules_in_block_to_quantize": null,
"pad_token_id": null,
"quant_method": "gptq",
"sym": true,
"tokenizer": null,
"true_sequential": true,
"use_cuda_fp16": false,
"use_exllama": true
},
"rope_theta": 75000000.0,
"torch_dtype": "float16",
"transformers_version": "4.42.4",
"use_cache": true,
"use_qk_norm": true,
"vocab_size": 256000
}
|