reka-flash-3-W8A8 / .ipynb_checkpoints /config-checkpoint.json
noneUsername's picture
Upload folder using huggingface_hub
699502b verified
{
"_name_or_path": "/root/autodl-tmp/reka-flash-3",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 100257,
"eos_token_id": 100257,
"head_dim": 96,
"hidden_act": "silu",
"hidden_size": 6144,
"initializer_range": 0.006,
"intermediate_size": 19648,
"max_position_embeddings": 32768,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 44,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"quantization_config": {
"config_groups": {
"group_0": {
"input_activations": {
"actorder": null,
"block_structure": null,
"dynamic": true,
"group_size": null,
"num_bits": 8,
"observer": null,
"observer_kwargs": {},
"strategy": "token",
"symmetric": true,
"type": "int"
},
"output_activations": null,
"targets": [
"Linear"
],
"weights": {
"actorder": null,
"block_structure": null,
"dynamic": false,
"group_size": null,
"num_bits": 8,
"observer": "mse",
"observer_kwargs": {},
"strategy": "channel",
"symmetric": true,
"type": "int"
}
}
},
"format": "int-quantized",
"global_compression_ratio": 1.4610358386985147,
"ignore": [
"lm_head"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "compressed"
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 8000000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.47.1",
"use_cache": true,
"vocab_size": 100352
}