Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,100 @@
+{
+  "_name_or_path": "Qwen/Qwen2-57B-A14B-Instruct",
+  "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": 32768,
+  "max_window_layers": 28,
+  "mlp_only_layers": [],
+  "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,
+  "quantization_config": {
+    "activation_scheme": "static",
+    "ignored_layers": [
+      "model.layers.5.mlp.gate",
+      "model.layers.24.mlp.shared_expert_gate",
+      "model.layers.23.mlp.shared_expert_gate",
+      "model.layers.5.mlp.shared_expert_gate",
+      "model.layers.16.mlp.shared_expert_gate",
+      "model.layers.14.mlp.gate",
+      "model.layers.17.mlp.gate",
+      "model.layers.26.mlp.gate",
+      "model.layers.15.mlp.shared_expert_gate",
+      "lm_head",
+      "model.layers.2.mlp.shared_expert_gate",
+      "model.layers.3.mlp.gate",
+      "model.layers.12.mlp.shared_expert_gate",
+      "model.layers.27.mlp.shared_expert_gate",
+      "model.layers.2.mlp.gate",
+      "model.layers.7.mlp.shared_expert_gate",
+      "model.layers.6.mlp.gate",
+      "model.layers.19.mlp.gate",
+      "model.layers.20.mlp.gate",
+      "model.layers.7.mlp.gate",
+      "model.layers.11.mlp.shared_expert_gate",
+      "model.layers.17.mlp.shared_expert_gate",
+      "model.layers.21.mlp.shared_expert_gate",
+      "model.layers.1.mlp.shared_expert_gate",
+      "model.layers.0.mlp.shared_expert_gate",
+      "model.layers.9.mlp.shared_expert_gate",
+      "model.layers.18.mlp.shared_expert_gate",
+      "model.layers.8.mlp.gate",
+      "model.layers.14.mlp.shared_expert_gate",
+      "model.layers.4.mlp.shared_expert_gate",
+      "model.layers.26.mlp.shared_expert_gate",
+      "model.layers.27.mlp.gate",
+      "model.layers.15.mlp.gate",
+      "model.layers.19.mlp.shared_expert_gate",
+      "model.layers.13.mlp.shared_expert_gate",
+      "model.layers.20.mlp.shared_expert_gate",
+      "model.layers.9.mlp.gate",
+      "model.layers.3.mlp.shared_expert_gate",
+      "model.layers.22.mlp.gate",
+      "model.layers.22.mlp.shared_expert_gate",
+      "model.layers.12.mlp.gate",
+      "model.layers.13.mlp.gate",
+      "model.layers.1.mlp.gate",
+      "model.layers.11.mlp.gate",
+      "model.layers.16.mlp.gate",
+      "model.layers.21.mlp.gate",
+      "model.layers.8.mlp.shared_expert_gate",
+      "model.layers.25.mlp.shared_expert_gate",
+      "model.layers.4.mlp.gate",
+      "model.layers.6.mlp.shared_expert_gate",
+      "model.layers.23.mlp.gate",
+      "model.layers.10.mlp.shared_expert_gate",
+      "model.layers.24.mlp.gate",
+      "model.layers.10.mlp.gate",
+      "model.layers.25.mlp.gate",
+      "model.layers.18.mlp.gate",
+      "model.layers.0.mlp.gate"
+    ],
+    "quant_method": "fp8"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 20480,
+  "sliding_window": 65536,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b0dd7254c99b42b05b48f8c2521f89f3a7e5929b65265480d8c698f2dd4c26
+size 4965711072

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:427b0110746ad20ce0cd0830de014485d1e14e8774db9f76b609c12a386c1f83
+size 4998368568

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dedcc45c4ed5c9dfef142c9c0ed11d36d84944811f98875a5751a5bd8a86e078
+size 4986872640

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb44ef86081bde9273a95af3390762c7aee4733fb65c356d4e18277be1ba1bb
+size 4998366136

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f10fcabee60d9eedcf7849338eaad99907f336754be4190dc72b585dcac3b900
+size 4996049200

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1881ec465ce5f29602e5f917ee075288247c767894bcd07e1c1f34b802926fdd
+size 4998367600

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ac575f2191d30cd86356c23ec9b6c73fa5fcb4375fe773b6d6b7d16849ddea
+size 4996049552

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49784acd9b2665f01f84269fb8a9d10f4c2f05d206593a7908f7f7995e8a48b
+size 4998367584

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de5320cf6fe2730b7a29faff1c9b614066cdfaa3aedbb945c7f0cd967b9f9001
+size 4996049552

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2595f90ea8129b50b038fecb30c61b97b9532621da8001b32877513870ae0a
+size 4998367592

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c41331d81fbd31b379f72a329f21cab56a82d2b1c248186a7ee29c39bed05bc
+size 4996049544

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcac8021f7460dfcbb0aad5afc1c829683bdc80843e88e27a15f38b164c6f0a7
+size 3577948360

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "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 +1,43 @@
+{
+  "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 %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 65536,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}