File size: 1,099 Bytes
1ca40e2 |
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 |
{
"_name_or_path": "SpectraSuite/FloatLM_830M",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"dims_per_head": 64,
"eos_token_id": 0,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 24,
"num_hidden_layers": 24,
"num_key_value_heads": 24,
"pretraining_tp": 1,
"quantization_config": {
"bits": 2,
"damp_percent": 0.1,
"dataset": "wikitext2",
"desc_act": false,
"group_size": 128,
"modules_in_block_to_quantize": null,
"quant_method": "gptq",
"sym": true,
"true_sequential": true
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"rotary_emb_base": 10000,
"rotary_pct": 1.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.41.2",
"use_cache": true,
"use_parallel_residual": false,
"vocab_size": 50304
}
|