Tess-M-34B-2bit / config.json
KnutJaegersberg's picture
Upload 10 files
261488c
{
"_name_or_path": "/run/media/knut/HD2/LLMs2/40b/fine-tuned/Tess-34B-v1.4",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 64000,
"eos_token_id": 64001,
"hidden_act": "silu",
"hidden_size": 7168,
"initializer_range": 0.02,
"intermediate_size": 20480,
"max_position_embeddings": 200000,
"model_type": "llama",
"num_attention_heads": 56,
"num_hidden_layers": 60,
"num_key_value_heads": 8,
"pad_token_id": 0,
"pretraining_tp": 1,
"quip_params": {
"codebook": "E8P12",
"codebook_version": 1,
"codesz": 8,
"fused": true,
"idx_dtype": "torch.int64",
"lora_rank": 0,
"model_version": 1,
"outlier_channel_split": false,
"packsz": 4,
"rescale_WH": false
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 5000000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.34.0",
"use_cache": false,
"vocab_size": 64002
}