Upload folder using huggingface_hub

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "Qwen2MoeForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2_moe",
+  "moe_intermediate_size": 2560,
+  "norm_topk_prob": false,
+  "num_attention_heads": 28,
+  "num_experts": 64,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 20480,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration.json

@@ -0,0 +1,5 @@
+{
+    "framework": "pytorch",
+    "task": "fill-mask",
+    "allow_remote": true
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "transformers_version": "4.40.0.dev0"
+}

model-00001-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495ce877ea894cc5288c3d5563b010fa02e37d5fca5cda3b8c2f9cea8d713596
+size 3992548152

model-00002-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f489a8aa239044c293884b3d2dd09fa281067a46574491bf39a984ba9f1572
+size 3986152016

model-00003-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ab5680d17f3c8781000c613e476c20929355ef5bfb71e92835615ebe9a985bc
+size 3986152008

model-00004-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:425682167a97800c8d3a11132ce7c500ba9e1285b1d1553891c0cc5207f99c5c
+size 3986152008

model-00005-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:173e9719fb2938633dc2424d82be4f1e330757d6684b9df862b1753c6964269e
+size 3986152000

model-00006-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ade2654e7a111cefeae0b801645f6923fd4b4ea1411fa90929d9124ea4f356
+size 3986152000

model-00007-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d894c920f3dc19691ccd8293b89beff3802c6a0ce0e07550707310ace2d44843
+size 3986151992

model-00008-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7506bb2544919c96747db518427f1ed842ea92ad014b40ab1a9f711381615773
+size 3986151992

model-00009-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0c9d82287cdfb0c0a68114af66a098566172d6519d91e69088de0b742c6b684
+size 3986151992

model-00010-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d8205714ef86e0121e94cd45a4750f8f94791d831083c3e5f3cca1727073af
+size 3986151984

model-00011-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181a3aa0abecec8e2556d71bb61b2d0417ce751e340b62c1408bc12dbe7b7ab7
+size 3986152136

model-00012-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d988b24ec4360e90933c1ad734867e7b36090f9ce7df7e3390d69693bfcfe4b0
+size 3986152184

model-00013-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d484a9fbe9560c8e086289d7bbe4836f13b467f0a2ff9d3e0e377ab03fa020
+size 3986152184

model-00014-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62f99e599dad7d5bd7e93e5c03b1a5f703883b26b74d8044a62bab3d84969168
+size 3986152184

model-00015-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d93d519092d3cb5d617a71a271b161247474c35709e93fd371aeb4179d729cb2
+size 3986152184

model-00016-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ce5228bbab221c9e4f582442d8578d8389e919078e8870d42fa718fa9828f66
+size 3986152184

model-00017-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d82ecbc26aeef5ef355b241e679e4b977a4ac3e7decec90aed648b9e6fdbde42
+size 3986152184

model-00018-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde6491980a5918f40541e066f7266054a711e39949ee6311ead8a4a5124c991
+size 3986152184

model-00019-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd464c2194cb02cd8e719329fa7ac0355f9c6f37ed35ebee7b38e997647a4821
+size 3986152184

model-00020-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb3b87aac0c3c48b25bef187f1aaff23de3368cf9b285ba824d5efa6eb394c5
+size 3986152184

model-00021-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c409edbe65f068c9dd340fd4cb42fecf1d62c10ce0d7645dc982a50122704ed6
+size 3986152184

model-00022-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0808d691fdb73a37136254c2f2549d643eba479a34f17b2e6447652a3e21f008
+size 3986152184

model-00023-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091c717fecaf6cf1f9922a44dec1323832c69b8358681bc58dff549fe0b6507f
+size 3986152184

model-00024-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3764562cdc1da5964652fa79cdbfd55775ad52b4783e2b03704e94c5455696a
+size 3986152184

model-00025-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dcadeedfdd774520240ff5abfd6352b0999f7bfc55573546d2272cb11d8bf00
+size 3986152184

model-00026-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcdd3de0516a56ad68685fe762b4952ddbd7d5a4a5d3276cbd51c5e207c96028
+size 3986152184

model-00027-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f8d585bbfc1dd6870e0c68377f25d5c4d0bc033b8445539a76e89a3f199607e
+size 3986152184

model-00028-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab77ad8efee4619032574596b4456117a7a58c23b561c4ef45e879c8bde0f703
+size 3986152184

model-00029-of-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e9ee070bf3b9b49768a5fd6b7fbfcca4445f9842536ed72e41711370e69b81
+size 3199377488

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
+