Upload NllbMoeForConditionalGeneration

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "facebook/nllb-moe-54b",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "NllbMoeForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "batch_prioritized_routing": false,
+  "bos_token_id": 0,
+  "d_model": 2048,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 8192,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 24,
+  "decoder_sparse_step": 4,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 8192,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 24,
+  "encoder_sparse_step": 4,
+  "eos_token_id": 2,
+  "expert_capacity": 64,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "nllb-moe",
+  "moe_eval_capacity_token_fraction": 1.0,
+  "moe_token_dropout": 0.2,
+  "normalize_router_prob_before_dropping": false,
+  "num_experts": 128,
+  "num_hidden_layers": 24,
+  "output_router_logits": false,
+  "pad_token_id": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true
+  },
+  "router_aux_loss_coef": 0.001,
+  "router_bias": false,
+  "router_dtype": "float32",
+  "router_ignore_padding_tokens": false,
+  "router_jitter_noise": 0.01,
+  "router_type": "tokens_masked",
+  "router_z_loss_coef": 0.001,
+  "scale_embedding": true,
+  "second_expert_policy": "all",
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 256206
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_new_tokens": 200,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.30.2"
+}

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4462da4697350947e92ec8ef997a4f2cf78ca6220c5b1a5a74cbe247a553d4e
+size 9987344418

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92860ca02a7b3032f517161c319fcc9e07d5fc199cf669a64c84c060a880784a
+size 9985422674

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3963caae7bf5a08f06194051ae8063535a16c7679887d2f27de0800a0cec6fb4
+size 8960069066

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9554413c7455412f0b14804f7e2f2a5f6a75a09130897d494be2d1843cbbf85
+size 9997120618

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00e4d0e4e256de68bf3b74d57425c46f2ab3d63a0dfd32382a52f1e41a40bd3
+size 9986212938

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428ef4f1559b6ebd5cac14d9da3ae03018f5e77e12dc3f59a5fd7d8fc448cb92
+size 8304235178