flozi00's picture
Upload MixtralForCausalLM
3f8b7a9 verified
raw
history blame
1.91 kB
{
"_name_or_path": "/volume_hf/models--VAGOsolutions--SauerkrautLM-Mixtral-8x7B-Instruct/snapshots/30ed549de7d84f68b4c6cb619f73275c99af23cc",
"architectures": [
"MixtralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"compression_config": {
"config_groups": {
"group_0": {
"input_activations": {
"block_structure": null,
"dynamic": true,
"group_size": null,
"num_bits": 8,
"observer": "memoryless",
"observer_kwargs": {},
"strategy": "token",
"symmetric": true,
"type": "float"
},
"output_activations": null,
"targets": [
"Linear"
],
"weights": {
"block_structure": null,
"dynamic": false,
"group_size": null,
"num_bits": 8,
"observer": "minmax",
"observer_kwargs": {},
"strategy": "channel",
"symmetric": true,
"type": "float"
}
}
},
"format": "float-quantized",
"global_compression_ratio": 1.2655668094430201,
"ignore": [
"lm_head"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "frozen"
},
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mixtral",
"num_attention_heads": 32,
"num_experts_per_tok": 2,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"num_local_experts": 8,
"output_router_logits": false,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"router_aux_loss_coef": 0.02,
"router_jitter_noise": 0.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.44.2",
"use_cache": true,
"vocab_size": 32000
}