Add files using upload-large-folder tool

config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "GlmMoeDsaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "ep_size": 1,
+  "first_k_dense_replace": 3,
+  "hidden_act": "silu",
+  "head_dim": 64,
+  "hidden_size": 6144,
+  "index_head_dim": 128,
+  "index_n_heads": 32,
+  "index_topk": 2048,
+  "indexer_rope_interleave": true,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 202752,
+  "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
+  "model_type": "glm_moe_dsa",
+  "n_group": 1,
+  "n_routed_experts": 256,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 78,
+  "num_key_value_heads": 64,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 154820,
+  "pretraining_tp": 1,
+  "q_lora_rank": 2048,
+  "qk_head_dim": 256,
+  "qk_nope_head_dim": 192,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-05,
+  "rope_interleave": true,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "transformers_version": "5.0.2.dev0",
+  "use_cache": true,
+  "v_head_dim": 256,
+  "vocab_size": 154880
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "pad_token_id": 154820,
+  "temperature": 1.0,
+  "top_p": 0.95,
+  "transformers_version": "5.0.2.dev0"
+}

hf_quant_config.json

@@ -0,0 +1,405 @@
+{
+    "producer": {
+        "name": "modelopt",
+        "version": "0.42.0rc1.dev17+g7430041bd.d20260212"
+    },
+    "quantization": {
+        "quant_algo": "NVFP4",
+        "kv_cache_quant_algo": "FP8",
+        "group_size": 16,
+        "exclude_modules": [
+            "lm_head",
+            "model.layers.0.self_attn.indexer*",
+            "model.layers.0.self_attn.kv_a_proj_with_mqa",
+            "model.layers.0.self_attn.kv_b_proj",
+            "model.layers.0.self_attn.q_a_proj",
+            "model.layers.0.self_attn.q_b_proj",
+            "model.layers.1.self_attn.indexer*",
+            "model.layers.1.self_attn.kv_a_proj_with_mqa",
+            "model.layers.1.self_attn.kv_b_proj",
+            "model.layers.1.self_attn.q_a_proj",
+            "model.layers.1.self_attn.q_b_proj",
+            "model.layers.10.self_attn.indexer*",
+            "model.layers.10.self_attn.kv_a_proj_with_mqa",
+            "model.layers.10.self_attn.kv_b_proj",
+            "model.layers.10.self_attn.q_a_proj",
+            "model.layers.10.self_attn.q_b_proj",
+            "model.layers.11.self_attn.indexer*",
+            "model.layers.11.self_attn.kv_a_proj_with_mqa",
+            "model.layers.11.self_attn.kv_b_proj",
+            "model.layers.11.self_attn.q_a_proj",
+            "model.layers.11.self_attn.q_b_proj",
+            "model.layers.12.self_attn.indexer*",
+            "model.layers.12.self_attn.kv_a_proj_with_mqa",
+            "model.layers.12.self_attn.kv_b_proj",
+            "model.layers.12.self_attn.q_a_proj",
+            "model.layers.12.self_attn.q_b_proj",
+            "model.layers.13.self_attn.indexer*",
+            "model.layers.13.self_attn.kv_a_proj_with_mqa",
+            "model.layers.13.self_attn.kv_b_proj",
+            "model.layers.13.self_attn.q_a_proj",
+            "model.layers.13.self_attn.q_b_proj",
+            "model.layers.14.self_attn.indexer*",
+            "model.layers.14.self_attn.kv_a_proj_with_mqa",
+            "model.layers.14.self_attn.kv_b_proj",
+            "model.layers.14.self_attn.q_a_proj",
+            "model.layers.14.self_attn.q_b_proj",
+            "model.layers.15.self_attn.indexer*",
+            "model.layers.15.self_attn.kv_a_proj_with_mqa",
+            "model.layers.15.self_attn.kv_b_proj",
+            "model.layers.15.self_attn.q_a_proj",
+            "model.layers.15.self_attn.q_b_proj",
+            "model.layers.16.self_attn.indexer*",
+            "model.layers.16.self_attn.kv_a_proj_with_mqa",
+            "model.layers.16.self_attn.kv_b_proj",
+            "model.layers.16.self_attn.q_a_proj",
+            "model.layers.16.self_attn.q_b_proj",
+            "model.layers.17.self_attn.indexer*",
+            "model.layers.17.self_attn.kv_a_proj_with_mqa",
+            "model.layers.17.self_attn.kv_b_proj",
+            "model.layers.17.self_attn.q_a_proj",
+            "model.layers.17.self_attn.q_b_proj",
+            "model.layers.18.self_attn.indexer*",
+            "model.layers.18.self_attn.kv_a_proj_with_mqa",
+            "model.layers.18.self_attn.kv_b_proj",
+            "model.layers.18.self_attn.q_a_proj",
+            "model.layers.18.self_attn.q_b_proj",
+            "model.layers.19.self_attn.indexer*",
+            "model.layers.19.self_attn.kv_a_proj_with_mqa",
+            "model.layers.19.self_attn.kv_b_proj",
+            "model.layers.19.self_attn.q_a_proj",
+            "model.layers.19.self_attn.q_b_proj",
+            "model.layers.2.self_attn.indexer*",
+            "model.layers.2.self_attn.kv_a_proj_with_mqa",
+            "model.layers.2.self_attn.kv_b_proj",
+            "model.layers.2.self_attn.q_a_proj",
+            "model.layers.2.self_attn.q_b_proj",
+            "model.layers.20.self_attn.indexer*",
+            "model.layers.20.self_attn.kv_a_proj_with_mqa",
+            "model.layers.20.self_attn.kv_b_proj",
+            "model.layers.20.self_attn.q_a_proj",
+            "model.layers.20.self_attn.q_b_proj",
+            "model.layers.21.self_attn.indexer*",
+            "model.layers.21.self_attn.kv_a_proj_with_mqa",
+            "model.layers.21.self_attn.kv_b_proj",
+            "model.layers.21.self_attn.q_a_proj",
+            "model.layers.21.self_attn.q_b_proj",
+            "model.layers.22.self_attn.indexer*",
+            "model.layers.22.self_attn.kv_a_proj_with_mqa",
+            "model.layers.22.self_attn.kv_b_proj",
+            "model.layers.22.self_attn.q_a_proj",
+            "model.layers.22.self_attn.q_b_proj",
+            "model.layers.23.self_attn.indexer*",
+            "model.layers.23.self_attn.kv_a_proj_with_mqa",
+            "model.layers.23.self_attn.kv_b_proj",
+            "model.layers.23.self_attn.q_a_proj",
+            "model.layers.23.self_attn.q_b_proj",
+            "model.layers.24.self_attn.indexer*",
+            "model.layers.24.self_attn.kv_a_proj_with_mqa",
+            "model.layers.24.self_attn.kv_b_proj",
+            "model.layers.24.self_attn.q_a_proj",
+            "model.layers.24.self_attn.q_b_proj",
+            "model.layers.25.self_attn.indexer*",
+            "model.layers.25.self_attn.kv_a_proj_with_mqa",
+            "model.layers.25.self_attn.kv_b_proj",
+            "model.layers.25.self_attn.q_a_proj",
+            "model.layers.25.self_attn.q_b_proj",
+            "model.layers.26.self_attn.indexer*",
+            "model.layers.26.self_attn.kv_a_proj_with_mqa",
+            "model.layers.26.self_attn.kv_b_proj",
+            "model.layers.26.self_attn.q_a_proj",
+            "model.layers.26.self_attn.q_b_proj",
+            "model.layers.27.self_attn.indexer*",
+            "model.layers.27.self_attn.kv_a_proj_with_mqa",
+            "model.layers.27.self_attn.kv_b_proj",
+            "model.layers.27.self_attn.q_a_proj",
+            "model.layers.27.self_attn.q_b_proj",
+            "model.layers.28.self_attn.indexer*",
+            "model.layers.28.self_attn.kv_a_proj_with_mqa",
+            "model.layers.28.self_attn.kv_b_proj",
+            "model.layers.28.self_attn.q_a_proj",
+            "model.layers.28.self_attn.q_b_proj",
+            "model.layers.29.self_attn.indexer*",
+            "model.layers.29.self_attn.kv_a_proj_with_mqa",
+            "model.layers.29.self_attn.kv_b_proj",
+            "model.layers.29.self_attn.q_a_proj",
+            "model.layers.29.self_attn.q_b_proj",
+            "model.layers.3.self_attn.indexer*",
+            "model.layers.3.self_attn.kv_a_proj_with_mqa",
+            "model.layers.3.self_attn.kv_b_proj",
+            "model.layers.3.self_attn.q_a_proj",
+            "model.layers.3.self_attn.q_b_proj",
+            "model.layers.30.self_attn.indexer*",
+            "model.layers.30.self_attn.kv_a_proj_with_mqa",
+            "model.layers.30.self_attn.kv_b_proj",
+            "model.layers.30.self_attn.q_a_proj",
+            "model.layers.30.self_attn.q_b_proj",
+            "model.layers.31.self_attn.indexer*",
+            "model.layers.31.self_attn.kv_a_proj_with_mqa",
+            "model.layers.31.self_attn.kv_b_proj",
+            "model.layers.31.self_attn.q_a_proj",
+            "model.layers.31.self_attn.q_b_proj",
+            "model.layers.32.self_attn.indexer*",
+            "model.layers.32.self_attn.kv_a_proj_with_mqa",
+            "model.layers.32.self_attn.kv_b_proj",
+            "model.layers.32.self_attn.q_a_proj",
+            "model.layers.32.self_attn.q_b_proj",
+            "model.layers.33.self_attn.indexer*",
+            "model.layers.33.self_attn.kv_a_proj_with_mqa",
+            "model.layers.33.self_attn.kv_b_proj",
+            "model.layers.33.self_attn.q_a_proj",
+            "model.layers.33.self_attn.q_b_proj",
+            "model.layers.34.self_attn.indexer*",
+            "model.layers.34.self_attn.kv_a_proj_with_mqa",
+            "model.layers.34.self_attn.kv_b_proj",
+            "model.layers.34.self_attn.q_a_proj",
+            "model.layers.34.self_attn.q_b_proj",
+            "model.layers.35.self_attn.indexer*",
+            "model.layers.35.self_attn.kv_a_proj_with_mqa",
+            "model.layers.35.self_attn.kv_b_proj",
+            "model.layers.35.self_attn.q_a_proj",
+            "model.layers.35.self_attn.q_b_proj",
+            "model.layers.36.self_attn.indexer*",
+            "model.layers.36.self_attn.kv_a_proj_with_mqa",
+            "model.layers.36.self_attn.kv_b_proj",
+            "model.layers.36.self_attn.q_a_proj",
+            "model.layers.36.self_attn.q_b_proj",
+            "model.layers.37.self_attn.indexer*",
+            "model.layers.37.self_attn.kv_a_proj_with_mqa",
+            "model.layers.37.self_attn.kv_b_proj",
+            "model.layers.37.self_attn.q_a_proj",
+            "model.layers.37.self_attn.q_b_proj",
+            "model.layers.38.self_attn.indexer*",
+            "model.layers.38.self_attn.kv_a_proj_with_mqa",
+            "model.layers.38.self_attn.kv_b_proj",
+            "model.layers.38.self_attn.q_a_proj",
+            "model.layers.38.self_attn.q_b_proj",
+            "model.layers.39.self_attn.indexer*",
+            "model.layers.39.self_attn.kv_a_proj_with_mqa",
+            "model.layers.39.self_attn.kv_b_proj",
+            "model.layers.39.self_attn.q_a_proj",
+            "model.layers.39.self_attn.q_b_proj",
+            "model.layers.4.self_attn.indexer*",
+            "model.layers.4.self_attn.kv_a_proj_with_mqa",
+            "model.layers.4.self_attn.kv_b_proj",
+            "model.layers.4.self_attn.q_a_proj",
+            "model.layers.4.self_attn.q_b_proj",
+            "model.layers.40.self_attn.indexer*",
+            "model.layers.40.self_attn.kv_a_proj_with_mqa",
+            "model.layers.40.self_attn.kv_b_proj",
+            "model.layers.40.self_attn.q_a_proj",
+            "model.layers.40.self_attn.q_b_proj",
+            "model.layers.41.self_attn.indexer*",
+            "model.layers.41.self_attn.kv_a_proj_with_mqa",
+            "model.layers.41.self_attn.kv_b_proj",
+            "model.layers.41.self_attn.q_a_proj",
+            "model.layers.41.self_attn.q_b_proj",
+            "model.layers.42.self_attn.indexer*",
+            "model.layers.42.self_attn.kv_a_proj_with_mqa",
+            "model.layers.42.self_attn.kv_b_proj",
+            "model.layers.42.self_attn.q_a_proj",
+            "model.layers.42.self_attn.q_b_proj",
+            "model.layers.43.self_attn.indexer*",
+            "model.layers.43.self_attn.kv_a_proj_with_mqa",
+            "model.layers.43.self_attn.kv_b_proj",
+            "model.layers.43.self_attn.q_a_proj",
+            "model.layers.43.self_attn.q_b_proj",
+            "model.layers.44.self_attn.indexer*",
+            "model.layers.44.self_attn.kv_a_proj_with_mqa",
+            "model.layers.44.self_attn.kv_b_proj",
+            "model.layers.44.self_attn.q_a_proj",
+            "model.layers.44.self_attn.q_b_proj",
+            "model.layers.45.self_attn.indexer*",
+            "model.layers.45.self_attn.kv_a_proj_with_mqa",
+            "model.layers.45.self_attn.kv_b_proj",
+            "model.layers.45.self_attn.q_a_proj",
+            "model.layers.45.self_attn.q_b_proj",
+            "model.layers.46.self_attn.indexer*",
+            "model.layers.46.self_attn.kv_a_proj_with_mqa",
+            "model.layers.46.self_attn.kv_b_proj",
+            "model.layers.46.self_attn.q_a_proj",
+            "model.layers.46.self_attn.q_b_proj",
+            "model.layers.47.self_attn.indexer*",
+            "model.layers.47.self_attn.kv_a_proj_with_mqa",
+            "model.layers.47.self_attn.kv_b_proj",
+            "model.layers.47.self_attn.q_a_proj",
+            "model.layers.47.self_attn.q_b_proj",
+            "model.layers.48.self_attn.indexer*",
+            "model.layers.48.self_attn.kv_a_proj_with_mqa",
+            "model.layers.48.self_attn.kv_b_proj",
+            "model.layers.48.self_attn.q_a_proj",
+            "model.layers.48.self_attn.q_b_proj",
+            "model.layers.49.self_attn.indexer*",
+            "model.layers.49.self_attn.kv_a_proj_with_mqa",
+            "model.layers.49.self_attn.kv_b_proj",
+            "model.layers.49.self_attn.q_a_proj",
+            "model.layers.49.self_attn.q_b_proj",
+            "model.layers.5.self_attn.indexer*",
+            "model.layers.5.self_attn.kv_a_proj_with_mqa",
+            "model.layers.5.self_attn.kv_b_proj",
+            "model.layers.5.self_attn.q_a_proj",
+            "model.layers.5.self_attn.q_b_proj",
+            "model.layers.50.self_attn.indexer*",
+            "model.layers.50.self_attn.kv_a_proj_with_mqa",
+            "model.layers.50.self_attn.kv_b_proj",
+            "model.layers.50.self_attn.q_a_proj",
+            "model.layers.50.self_attn.q_b_proj",
+            "model.layers.51.self_attn.indexer*",
+            "model.layers.51.self_attn.kv_a_proj_with_mqa",
+            "model.layers.51.self_attn.kv_b_proj",
+            "model.layers.51.self_attn.q_a_proj",
+            "model.layers.51.self_attn.q_b_proj",
+            "model.layers.52.self_attn.indexer*",
+            "model.layers.52.self_attn.kv_a_proj_with_mqa",
+            "model.layers.52.self_attn.kv_b_proj",
+            "model.layers.52.self_attn.q_a_proj",
+            "model.layers.52.self_attn.q_b_proj",
+            "model.layers.53.self_attn.indexer*",
+            "model.layers.53.self_attn.kv_a_proj_with_mqa",
+            "model.layers.53.self_attn.kv_b_proj",
+            "model.layers.53.self_attn.q_a_proj",
+            "model.layers.53.self_attn.q_b_proj",
+            "model.layers.54.self_attn.indexer*",
+            "model.layers.54.self_attn.kv_a_proj_with_mqa",
+            "model.layers.54.self_attn.kv_b_proj",
+            "model.layers.54.self_attn.q_a_proj",
+            "model.layers.54.self_attn.q_b_proj",
+            "model.layers.55.self_attn.indexer*",
+            "model.layers.55.self_attn.kv_a_proj_with_mqa",
+            "model.layers.55.self_attn.kv_b_proj",
+            "model.layers.55.self_attn.q_a_proj",
+            "model.layers.55.self_attn.q_b_proj",
+            "model.layers.56.self_attn.indexer*",
+            "model.layers.56.self_attn.kv_a_proj_with_mqa",
+            "model.layers.56.self_attn.kv_b_proj",
+            "model.layers.56.self_attn.q_a_proj",
+            "model.layers.56.self_attn.q_b_proj",
+            "model.layers.57.self_attn.indexer*",
+            "model.layers.57.self_attn.kv_a_proj_with_mqa",
+            "model.layers.57.self_attn.kv_b_proj",
+            "model.layers.57.self_attn.q_a_proj",
+            "model.layers.57.self_attn.q_b_proj",
+            "model.layers.58.self_attn.indexer*",
+            "model.layers.58.self_attn.kv_a_proj_with_mqa",
+            "model.layers.58.self_attn.kv_b_proj",
+            "model.layers.58.self_attn.q_a_proj",
+            "model.layers.58.self_attn.q_b_proj",
+            "model.layers.59.self_attn.indexer*",
+            "model.layers.59.self_attn.kv_a_proj_with_mqa",
+            "model.layers.59.self_attn.kv_b_proj",
+            "model.layers.59.self_attn.q_a_proj",
+            "model.layers.59.self_attn.q_b_proj",
+            "model.layers.6.self_attn.indexer*",
+            "model.layers.6.self_attn.kv_a_proj_with_mqa",
+            "model.layers.6.self_attn.kv_b_proj",
+            "model.layers.6.self_attn.q_a_proj",
+            "model.layers.6.self_attn.q_b_proj",
+            "model.layers.60.self_attn.indexer*",
+            "model.layers.60.self_attn.kv_a_proj_with_mqa",
+            "model.layers.60.self_attn.kv_b_proj",
+            "model.layers.60.self_attn.q_a_proj",
+            "model.layers.60.self_attn.q_b_proj",
+            "model.layers.61.self_attn.indexer*",
+            "model.layers.61.self_attn.kv_a_proj_with_mqa",
+            "model.layers.61.self_attn.kv_b_proj",
+            "model.layers.61.self_attn.q_a_proj",
+            "model.layers.61.self_attn.q_b_proj",
+            "model.layers.62.self_attn.indexer*",
+            "model.layers.62.self_attn.kv_a_proj_with_mqa",
+            "model.layers.62.self_attn.kv_b_proj",
+            "model.layers.62.self_attn.q_a_proj",
+            "model.layers.62.self_attn.q_b_proj",
+            "model.layers.63.self_attn.indexer*",
+            "model.layers.63.self_attn.kv_a_proj_with_mqa",
+            "model.layers.63.self_attn.kv_b_proj",
+            "model.layers.63.self_attn.q_a_proj",
+            "model.layers.63.self_attn.q_b_proj",
+            "model.layers.64.self_attn.indexer*",
+            "model.layers.64.self_attn.kv_a_proj_with_mqa",
+            "model.layers.64.self_attn.kv_b_proj",
+            "model.layers.64.self_attn.q_a_proj",
+            "model.layers.64.self_attn.q_b_proj",
+            "model.layers.65.self_attn.indexer*",
+            "model.layers.65.self_attn.kv_a_proj_with_mqa",
+            "model.layers.65.self_attn.kv_b_proj",
+            "model.layers.65.self_attn.q_a_proj",
+            "model.layers.65.self_attn.q_b_proj",
+            "model.layers.66.self_attn.indexer*",
+            "model.layers.66.self_attn.kv_a_proj_with_mqa",
+            "model.layers.66.self_attn.kv_b_proj",
+            "model.layers.66.self_attn.q_a_proj",
+            "model.layers.66.self_attn.q_b_proj",
+            "model.layers.67.self_attn.indexer*",
+            "model.layers.67.self_attn.kv_a_proj_with_mqa",
+            "model.layers.67.self_attn.kv_b_proj",
+            "model.layers.67.self_attn.q_a_proj",
+            "model.layers.67.self_attn.q_b_proj",
+            "model.layers.68.self_attn.indexer*",
+            "model.layers.68.self_attn.kv_a_proj_with_mqa",
+            "model.layers.68.self_attn.kv_b_proj",
+            "model.layers.68.self_attn.q_a_proj",
+            "model.layers.68.self_attn.q_b_proj",
+            "model.layers.69.self_attn.indexer*",
+            "model.layers.69.self_attn.kv_a_proj_with_mqa",
+            "model.layers.69.self_attn.kv_b_proj",
+            "model.layers.69.self_attn.q_a_proj",
+            "model.layers.69.self_attn.q_b_proj",
+            "model.layers.7.self_attn.indexer*",
+            "model.layers.7.self_attn.kv_a_proj_with_mqa",
+            "model.layers.7.self_attn.kv_b_proj",
+            "model.layers.7.self_attn.q_a_proj",
+            "model.layers.7.self_attn.q_b_proj",
+            "model.layers.70.self_attn.indexer*",
+            "model.layers.70.self_attn.kv_a_proj_with_mqa",
+            "model.layers.70.self_attn.kv_b_proj",
+            "model.layers.70.self_attn.q_a_proj",
+            "model.layers.70.self_attn.q_b_proj",
+            "model.layers.71.self_attn.indexer*",
+            "model.layers.71.self_attn.kv_a_proj_with_mqa",
+            "model.layers.71.self_attn.kv_b_proj",
+            "model.layers.71.self_attn.q_a_proj",
+            "model.layers.71.self_attn.q_b_proj",
+            "model.layers.72.self_attn.indexer*",
+            "model.layers.72.self_attn.kv_a_proj_with_mqa",
+            "model.layers.72.self_attn.kv_b_proj",
+            "model.layers.72.self_attn.q_a_proj",
+            "model.layers.72.self_attn.q_b_proj",
+            "model.layers.73.self_attn.indexer*",
+            "model.layers.73.self_attn.kv_a_proj_with_mqa",
+            "model.layers.73.self_attn.kv_b_proj",
+            "model.layers.73.self_attn.q_a_proj",
+            "model.layers.73.self_attn.q_b_proj",
+            "model.layers.74.self_attn.indexer*",
+            "model.layers.74.self_attn.kv_a_proj_with_mqa",
+            "model.layers.74.self_attn.kv_b_proj",
+            "model.layers.74.self_attn.q_a_proj",
+            "model.layers.74.self_attn.q_b_proj",
+            "model.layers.75.self_attn.indexer*",
+            "model.layers.75.self_attn.kv_a_proj_with_mqa",
+            "model.layers.75.self_attn.kv_b_proj",
+            "model.layers.75.self_attn.q_a_proj",
+            "model.layers.75.self_attn.q_b_proj",
+            "model.layers.76.self_attn.indexer*",
+            "model.layers.76.self_attn.kv_a_proj_with_mqa",
+            "model.layers.76.self_attn.kv_b_proj",
+            "model.layers.76.self_attn.q_a_proj",
+            "model.layers.76.self_attn.q_b_proj",
+            "model.layers.77.self_attn.indexer*",
+            "model.layers.77.self_attn.kv_a_proj_with_mqa",
+            "model.layers.77.self_attn.kv_b_proj",
+            "model.layers.77.self_attn.q_a_proj",
+            "model.layers.77.self_attn.q_b_proj",
+            "model.layers.8.self_attn.indexer*",
+            "model.layers.8.self_attn.kv_a_proj_with_mqa",
+            "model.layers.8.self_attn.kv_b_proj",
+            "model.layers.8.self_attn.q_a_proj",
+            "model.layers.8.self_attn.q_b_proj",
+            "model.layers.9.self_attn.indexer*",
+            "model.layers.9.self_attn.kv_a_proj_with_mqa",
+            "model.layers.9.self_attn.kv_b_proj",
+            "model.layers.9.self_attn.q_a_proj",
+            "model.layers.9.self_attn.q_b_proj",
+            "model.layers.78*"
+        ]
+    }
+}

model-00011-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b611112e5742c4b665345dd316417754b32c1e00cb6f6908366f77dd28dabdb
+size 1507692440

model-00014-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:296f3fa69ea56b0f36196cb4c118c1452739cc4d69f98f92cfc40817c5921727
+size 1507692536

model-00017-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee9e26a49e8c4c657787e0ebc8e95ea193f3621e5208e7687bf03bcb48e7c987
+size 1507692568

model-00020-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52fe48cc1f80e5e276dad3c203c27d6a1a8fc93783f3aa3f356c800113b0f109
+size 1615853792

model-00022-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6066d3666d9772cd2fb0dd547284bb4817bafafefe8643475515aa54239bc9c
+size 1507692456

model-00031-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94334f61b601bd5d36bbd201e2b5df89ab42b5697f4561762ba1129b1abffdef
+size 1615853696

model-00034-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e193a083d3e8fc176b4c42993ee275db8478cfb4ea7d62868dd458c006656be3
+size 1507691704

model-00037-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8508a402bca266d1112fcdf1e01bd3d262d055f4d3500777c574406f5e3e4a6b
+size 1507692272

model-00042-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093fbddb61434133cabe28d2ccafdaf0124d92d652750e1ff5a15cfb0c680c4b
+size 1615853352

model-00057-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ef1be63007ad3e38db4400993a15a100a8cb385317215c8d94885bec9b5dcc
+size 1615853784

model-00067-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243de0a847f83caabd6842484e8ce5b0b5344ee9e6ee00a4b518aa1475d87b8a
+size 1507691944

model-00068-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924416f239346b7b6aef4484629ee5f285737121ff87f0641bab14ab9adc41a1
+size 1615853696

model-00072-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce707f2eb704597e36afd417d8301d2430dcbf9c559cf6ebee5ee96cc5cbd702
+size 1615854224

model-00074-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642b40ece9fef237de0a3f10b4bc5830c30dfcf12871efbae554f9947ea6041d
+size 1507692272

model-00076-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0402fc392f0471e127e93f0dd4958a2faf9c8b130da5c735046c4801b996419
+size 1507691704

model-00077-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5c83f957ffd92e75874043d29af3010629b9cc2848c73d97b6396337a0796d3
+size 1507691696

model-00082-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:588f396c3ab8a5aaad2878921f49facdad6a50f3bf78ef5e8e6ff66ebfd90cf6
+size 1507691736

model-00091-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28cd890d97ca9a9da30839b285b0af3a043ed66704acde13c1be7507c50a3357
+size 1507692568

model-00103-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dddfe0243a0e71921d0cc2b62933d11dc6a00311753573394a69dbe7d7c28c3
+size 1507692544

model-00105-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142ecdc82c2997c75b91ae941fff6c4e6c894baa7d8db53bf55cad76f6242ba3
+size 1615853944

model-00113-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bb1b09984a046ff757be7254b0945e205dcbba93a7187d79f014df5f434657c
+size 1507692568

model-00118-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6725d5541e4ddb9828c20e451aabdac95a15bafa4f9d00707c7affff7c3095c
+size 1507691592

model-00125-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f096a536cf69d6654390977980dcdb1ae37da294e431440ce4136e908413fda
+size 1507692544

model-00127-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12796ee8ffe70e54a95c5bf1ef593cf770dd7f79e79e0b6347659debc0e8fee7
+size 1615853720

model-00130-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e865f1d3b899418db58a48bcb6f39301f5dd343e4176f0d3ef8d7b33d48ce09d
+size 1507691704

model-00157-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a10a3130b37023d7841a875e1ca1129492e87d81f841c82054e87074f461a60f
+size 1507691712

model-00159-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f67eac72b5ce0ec856e5b4daa210d54b16105bf78e6f985b8ac8a9ea028800f
+size 1507691224

model-00161-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13449de7cfc5229cae73a25d9dfe7419a5a528f760c65e91138bf5b3961ebd04
+size 1507692568

model-00163-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5540f68e4ad7dd7c1906b8417c13e7d78857ef630d23c75b837d9efbae8cdf05
+size 1507691808

model-00167-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2c6b6f0563aff1d5f29a2d505d8dfc205d4aa430730cb22ce228a6fba0aff4
+size 1502329784

model-00169-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3f77dfb67b713f3367c5081f395a80b9425cb44344fe3b1a7dd56ef3c7856c3
+size 1507692536

model-00194-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b1c8caeaf585a1d5530799d43bea46423ee3dc18e0a8672e08a2ab4e9a8a62
+size 1507692560

model-00215-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8f42c929d9c213f562eac85299403dfc6a904c97bd3a3fdf778ed83d91b79e
+size 1615853144

model-00221-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e694750fc37e89e6cfef5d8f53152f1f8f431a86e11425c26dc0f2e7fafbff4
+size 1507692544

model-00222-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36385554d703e42577d46d04d9532e0da626e9fbe802d748c987f02239a98038
+size 1507691808

model-00223-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c66374c7e75c52011c45094637ae2e960fab30ec40e1aad8c8d865a0f3ac5d
+size 1615853960

model-00230-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6280651f7873be8c9588ff2c61dc59bbb72c28cccbea3683c5ee3feb864fefb
+size 1615853328

model-00233-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b9fc2c73149b89f1ddbab4e6c1b81a978f986284df1f6dea5f00dab219fb1d2
+size 1507691896

model-00237-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e73b5623a04e1c5f35c43a2da3187ed8f27ec86f6e83222bb1a1edec0be2bba
+size 1507691720

model-00238-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19244eaa281f07826f86beac940aa49d6094d9be61aa056b42763651803ac129
+size 1615853608

model-00246-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:069f465dee2e46b93a66c096bf1cb7b1c6a34988301a6cb17764af390c528337
+size 1507692568

model-00266-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce8e1ef6cbfc9833bce15a84f54c8b1af19155c50b7a82536047058f4ffdf43
+size 1507692040

model-00269-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21dcb2244d49c96be7b0ce0446022aa157358437a4be390bed87f2bd1985ad5a
+size 1507692536

model-00278-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d35851aee8a4e9d9b33ae268759b37a6eb0d7f4cc41bbdb2aa1f64c949ad2621
+size 1615852576

model-00279-of-00282.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886d4011440f715cae202f66e2fac9976bb08b9e92f00594d2ac46191fa81ec0
+size 1507691704

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>"
+  ],
+  "is_local": true,
+  "model_max_length": 202752,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "TokenizersBackend"
+}