File size: 1,610 Bytes
4c5f3c6 f8231ec 4c5f3c6 f8231ec 4c5f3c6 |
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 55 56 57 58 59 60 61 62 63 64 65 66 |
{
"_name_or_path": "fxmarty/tiny-llama-fast-tokenizer",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"eos_token_id": 1,
"head_dim": 4,
"hidden_act": "silu",
"hidden_size": 16,
"initializer_range": 0.02,
"intermediate_size": 64,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 4,
"num_hidden_layers": 2,
"num_key_value_heads": 4,
"pad_token_id": -1,
"pretraining_tp": 1,
"quantization_config": {
"algo_config": null,
"exclude": [
"lm_head"
],
"export": {
"kv_cache_group": [],
"pack_method": "reorder",
"weight_format": "real_quantized",
"weight_merge_groups": null
},
"global_quant_config": {
"bias": null,
"input_tensors": null,
"output_tensors": null,
"target_device": null,
"weight": {
"ch_axis": null,
"dtype": "int8",
"group_size": null,
"is_dynamic": false,
"observer_cls": "PerTensorMinMaxObserver",
"qscheme": "per_tensor",
"round_method": "half_even",
"scale_type": "float",
"symmetric": true
}
},
"layer_quant_config": {},
"layer_type_quant_config": {},
"pack_method": "reorder",
"quant_method": "quark",
"quant_mode": "eager_mode"
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.45.2",
"use_cache": true,
"vocab_size": 32000
}
|