Upload folder using huggingface_hub

.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

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "Qwen35ForCausalLM"
+  ],
+  "model_type": "qwen35",
+  "hidden_size": 2048,
+  "intermediate_size": 6144,
+  "num_hidden_layers": 25,
+  "num_attention_heads": 8,
+  "num_key_value_heads": 2,
+  "max_position_embeddings": 262144,
+  "rms_norm_eps": 9.999999974752427e-07,
+  "rope_theta": 10000000.0,
+  "vocab_size": 248320,
+  "hidden_act": "silu",
+  "tie_word_embeddings": false,
+  "attention_bias": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.50.0",
+  "bos_token_id": 1,
+  "eos_token_id": 248046,
+  "_gguf_architecture": "qwen35",
+  "_gguf_file_type": 17,
+  "_original_name": "Merged_16Bit"
+}

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707cab45c5cde1f0b630c39f4fe3c350289d9d5d38b4ce782e723719bafa8b83
+size 3885340800

model.safetensors.index.json

@@ -0,0 +1,342 @@
+{
+  "metadata": {
+    "total_size": 3885306496
+  },
+  "weight_map": {
+    "blk.0.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.0.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.0.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.0.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.0.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.0.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.0.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.0.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.0.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.0.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.1.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.1.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.1.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.1.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.1.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.1.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.1.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.1.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.1.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.1.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.10.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.10.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.10.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.10.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.10.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.10.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.10.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.10.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.10.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.10.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.11.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.12.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.12.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.12.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.12.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.12.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.12.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.12.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.12.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.12.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.12.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.13.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.13.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.13.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.13.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.13.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.13.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.13.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.13.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.13.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.13.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.14.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.14.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.14.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.14.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.14.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.14.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.14.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.14.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.14.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.14.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.15.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.16.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.16.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.16.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.16.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.16.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.16.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.16.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.16.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.16.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.16.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.17.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.17.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.17.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.17.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.17.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.17.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.17.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.17.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.17.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.17.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.18.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.18.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.18.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.18.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.18.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.18.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.18.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.18.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.18.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.18.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.19.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.2.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.2.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.2.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.2.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.2.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.2.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.2.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.2.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.2.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.2.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.20.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.20.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.20.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.20.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.20.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.20.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.20.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.20.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.20.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.20.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.21.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.21.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.21.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.21.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.21.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.21.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.21.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.21.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.21.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.21.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.22.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.22.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.22.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.22.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.22.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.22.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.22.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.22.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.22.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.22.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.23.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.24.nextn.eh_proj.weight": "model-00001-of-00001.safetensors",
+    "blk.24.nextn.enorm.weight": "model-00001-of-00001.safetensors",
+    "blk.24.nextn.hnorm.weight": "model-00001-of-00001.safetensors",
+    "blk.24.nextn.shared_head_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.24.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.3.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.4.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.4.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.4.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.4.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.4.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.4.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.4.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.4.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.4.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.4.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.5.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.5.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.5.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.5.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.5.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.5.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.5.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.5.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.5.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.5.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.6.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.6.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.6.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.6.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.6.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.6.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.6.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.6.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.6.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.6.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.7.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.8.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.8.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.8.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.8.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.8.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.8.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.8.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.8.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.8.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.8.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "blk.9.attn_gate.weight": "model-00001-of-00001.safetensors",
+    "blk.9.attn_qkv.weight": "model-00001-of-00001.safetensors",
+    "blk.9.post_attention_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.9.ssm_a": "model-00001-of-00001.safetensors",
+    "blk.9.ssm_alpha.weight": "model-00001-of-00001.safetensors",
+    "blk.9.ssm_beta.weight": "model-00001-of-00001.safetensors",
+    "blk.9.ssm_conv1d.weight": "model-00001-of-00001.safetensors",
+    "blk.9.ssm_dt.bias": "model-00001-of-00001.safetensors",
+    "blk.9.ssm_norm.weight": "model-00001-of-00001.safetensors",
+    "blk.9.ssm_out.weight": "model-00001-of-00001.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.norm.weight": "model-00001-of-00001.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
+  "unk_token": "!",
+  "pad_token": "<|vision_pad|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9f876ad0ce182861e31954d9f5e4538356029d7dfbbcfd22690cefa059463b
+size 12816238

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
+  "unk_token": "!",
+  "pad_token": "<|vision_pad|>",
+  "model_max_length": 131072,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "clean_up_tokenization_spaces": false
+}