Configure Git LFS for large model files

.gitattributes

@@ -33,3 +33,10 @@ 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
+*.index.json filter=lfs diff=lfs merge=lfs -text
+merges.txt filter=lfs diff=lfs merge=lfs -text
+README.md filter=lfs diff=lfs merge=lfs -text
+recipe.yaml filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+chat_template.jinja filter=lfs diff=lfs merge=lfs -text
+tokenizer_config.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,4 +1,3 @@
----
-license: apache-2.0
----
-Temp
+version https://git-lfs.github.com/spec/v1
+oid sha256:d436dd151f7f319ce8580292bdf548302a5cbcffa8760cc9324f73a6417ee5ba
+size 32

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672e747c77e990320152343b0a4951222e40de5645297905d89afba05586d827
+size 6722

config.json

@@ -0,0 +1,147 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5472,
+  "max_position_embeddings": 524288,
+  "max_window_layers": 28,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 67,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "qkv_bias": false,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "pack-quantized",
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": "static",
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 128,
+          "num_bits": 4,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "model.layers.0.mlp.gate",
+      "model.layers.1.mlp.gate",
+      "model.layers.2.mlp.gate",
+      "model.layers.3.mlp.gate",
+      "model.layers.4.mlp.gate",
+      "model.layers.5.mlp.gate",
+      "model.layers.6.mlp.gate",
+      "model.layers.7.mlp.gate",
+      "model.layers.8.mlp.gate",
+      "model.layers.9.mlp.gate",
+      "model.layers.10.mlp.gate",
+      "model.layers.11.mlp.gate",
+      "model.layers.12.mlp.gate",
+      "model.layers.13.mlp.gate",
+      "model.layers.14.mlp.gate",
+      "model.layers.15.mlp.gate",
+      "model.layers.16.mlp.gate",
+      "model.layers.17.mlp.gate",
+      "model.layers.18.mlp.gate",
+      "model.layers.19.mlp.gate",
+      "model.layers.20.mlp.gate",
+      "model.layers.21.mlp.gate",
+      "model.layers.22.mlp.gate",
+      "model.layers.23.mlp.gate",
+      "model.layers.24.mlp.gate",
+      "model.layers.25.mlp.gate",
+      "model.layers.26.mlp.gate",
+      "model.layers.27.mlp.gate",
+      "model.layers.28.mlp.gate",
+      "model.layers.29.mlp.gate",
+      "model.layers.30.mlp.gate",
+      "model.layers.31.mlp.gate",
+      "model.layers.32.mlp.gate",
+      "model.layers.33.mlp.gate",
+      "model.layers.34.mlp.gate",
+      "model.layers.35.mlp.gate",
+      "model.layers.36.mlp.gate",
+      "model.layers.37.mlp.gate",
+      "model.layers.38.mlp.gate",
+      "model.layers.39.mlp.gate",
+      "model.layers.40.mlp.gate",
+      "model.layers.41.mlp.gate",
+      "model.layers.42.mlp.gate",
+      "model.layers.43.mlp.gate",
+      "model.layers.44.mlp.gate",
+      "model.layers.45.mlp.gate",
+      "model.layers.46.mlp.gate",
+      "model.layers.47.mlp.gate",
+      "model.layers.48.mlp.gate",
+      "model.layers.49.mlp.gate",
+      "model.layers.50.mlp.gate",
+      "model.layers.51.mlp.gate",
+      "model.layers.52.mlp.gate",
+      "model.layers.53.mlp.gate",
+      "model.layers.54.mlp.gate",
+      "model.layers.55.mlp.gate",
+      "model.layers.56.mlp.gate",
+      "model.layers.57.mlp.gate",
+      "model.layers.58.mlp.gate",
+      "model.layers.59.mlp.gate",
+      "model.layers.60.mlp.gate",
+      "model.layers.61.mlp.gate",
+      "model.layers.62.mlp.gate",
+      "model.layers.63.mlp.gate",
+      "model.layers.64.mlp.gate",
+      "model.layers.65.mlp.gate",
+      "model.layers.66.mlp.gate",
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.12.2"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 2.0,
+    "original_max_position_embeddings": 262144,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.0,
+  "shared_expert_intermediate_size": 0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_qk_norm": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 151645,
+  "transformers_version": "4.57.1"
+}

merges.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
+size 1671853

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56e975a98c7e83050076b9d7f70793ed57f7441197d1b753635470a7611c1660
+size 5001524144

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0810b0ac49377cd8f893f1cb6214cd1e4ad2fdaf1b2923c60e88a194a5b9cd9
+size 5001803304

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1142c828c7e313b9f8102ab6398e3152f90426b48d48f68dd41bd9e1f9a096e1
+size 5002084152

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02375548d249bfcdd586106c44682fb5969344058084060b5ea4690931f268c1
+size 5001803304

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62bd670173edc9e9bb1471b37dad3daa3e5d735610d9912693604ad25e470d89
+size 2800869152

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a90757ed987528ee18c7ddbf4c44d252fef7a7553d38c07ad2487423e1537f
+size 7560146

recipe.yaml

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da07e9dca21134a77d2ceb08e5d25701958fd61fd8d08b95603b5f705a6cfcc
+size 883

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0acdaba32b920d640afb36af4396c91974e074735636e4016d17a8ed9c03730
+size 11422753

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a2d456eb807c8368fe6b60101b1d1160d6889071a751ed08576b96e77e01cd
+size 5405