Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

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

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "/data/Qwen2-57B-A14B",
+  "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": 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,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 20480,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "transformers_version": "4.47.1"
+}

hf_quant_config.json

@@ -0,0 +1,10 @@
+{
+    "producer": {
+        "name": "modelopt",
+        "version": "0.25.0"
+    },
+    "quantization": {
+        "quant_algo": null,
+        "kv_cache_quant_algo": "FP8"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tllm-checkpoint/config.json

@@ -0,0 +1,65 @@
+{
+    "mlp_bias": false,
+    "attn_bias": false,
+    "rotary_base": 1000000.0,
+    "rotary_scaling": null,
+    "disable_weight_only_quant_plugin": false,
+    "num_labels": 1,
+    "use_logn_attn": false,
+    "moe": {
+        "num_experts": 64,
+        "shared_expert_intermediate_size": 20480,
+        "top_k": 8,
+        "normalization_mode": 0,
+        "sparse_mixer_epsilon": 0.01,
+        "tp_mode": 0,
+        "device_limited_n_group": 0,
+        "device_limited_topk_group": 0,
+        "device_limited_routed_scaling_factor": 1.0
+    },
+    "architecture": "Qwen2MoeForCausalLM",
+    "dtype": "bfloat16",
+    "vocab_size": 151936,
+    "hidden_size": 3584,
+    "num_hidden_layers": 28,
+    "num_attention_heads": 28,
+    "hidden_act": "swiglu",
+    "logits_dtype": "float32",
+    "norm_epsilon": 1e-06,
+    "runtime_defaults": null,
+    "position_embedding_type": "rope_gpt_neox",
+    "num_key_value_heads": 4,
+    "intermediate_size": 18944,
+    "max_position_embeddings": 131072,
+    "mapping": {
+        "world_size": 2,
+        "gpus_per_node": 8,
+        "cp_size": 1,
+        "tp_size": 2,
+        "pp_size": 1,
+        "moe_tp_size": 2,
+        "moe_ep_size": 1,
+        "auto_parallel": false
+    },
+    "quantization": {
+        "quant_algo": "FP8",
+        "kv_cache_quant_algo": "FP8",
+        "group_size": 128,
+        "smoothquant_val": 0.5,
+        "clamp_val": null,
+        "use_meta_recipe": false,
+        "has_zero_point": false,
+        "pre_quant_scale": false,
+        "exclude_modules": null
+    },
+    "use_parallel_embedding": false,
+    "embedding_sharding_dim": 0,
+    "head_size": 128,
+    "qk_layernorm": false,
+    "rotary_embedding_dim": 128,
+    "seq_length": 8192,
+    "qwen_type": "qwen2_moe",
+    "moe_intermediate_size": 2560,
+    "moe_shared_expert_intermediate_size": 20480,
+    "tie_word_embeddings": false
+}

tllm-checkpoint/rank0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2719d23f83e05b4faa021a776f5ed828defe393e5a8416cc8d846194586fc0f7
+size 26867556232

tllm-checkpoint/rank1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1c724344c5e1a24518402c11e70c530b616d45f0292b0c79ddf986633d5e1f
+size 26867556232

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb88da141e1d518cae1f7123f31e8d79b5762eeed8f1edff96183273415f3d7
+size 11418531

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}