File size: 1,096 Bytes
f21915c e46e90d f21915c e46e90d f21915c e46e90d f21915c e46e90d f21915c e46e90d f21915c e46e90d f21915c 1dbe99b f21915c |
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 |
{
"_name_or_path": "fxmarty/small-llama-testing",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"eos_token_id": 1,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 256,
"initializer_range": 0.02,
"intermediate_size": 128,
"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": {
"activation_scheme": "static",
"export": {
"kv_cache_group": [],
"min_kv_scale": 1.0,
"pack_method": "reorder",
"weight_format": "real_quantized",
"weight_merge_groups": null
},
"ignored_layers": [
"lm_head"
],
"kv_cache_scheme": null,
"quant_method": "fp8"
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.48.1",
"use_cache": true,
"vocab_size": 32000
}
|