Add files using upload-large-folder tool

README.md

@@ -0,0 +1,40 @@
+---
+library_name: mlx
+tags:
+- bitnet
+- falcon-e
+- mlx
+license: other
+license_name: falcon-llm-license
+license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
+pipeline_tag: text-generation
+base_model: tiiuae/Falcon-E-3B-Instruct
+---
+
+# mlx-community/Falcon-E-3B-Instruct-6bit
+
+This model [mlx-community/Falcon-E-3B-Instruct-6bit](https://huggingface.co/mlx-community/Falcon-E-3B-Instruct-6bit) was
+converted to MLX format from [tiiuae/Falcon-E-3B-Instruct](https://huggingface.co/tiiuae/Falcon-E-3B-Instruct)
+using mlx-lm version **0.25.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Falcon-E-3B-Instruct-6bit")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

config.json

@@ -0,0 +1,46 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 11,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 13312,
+    "is_bitnet_config": true,
+    "max_position_embeddings": 32768,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 2,
+    "pretraining_tp": 1,
+    "quantization": {
+        "group_size": 64,
+        "bits": 6,
+        "modules_to_not_convert": [
+            "lm_head"
+        ],
+        "quant_method": "bitnet"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 6,
+        "modules_to_not_convert": [
+            "lm_head"
+        ],
+        "quant_method": "bitnet"
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.47.0",
+    "use_cache": true,
+    "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [11, 228],
+  "transformers_version": "4.47.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd2f3b4952f51ffb821ed847012a6bc671f01a12867d46556b5b3e7ff18cbaca
+size 839185471

model.safetensors.index.json

@@ -0,0 +1,527 @@
+{
+    "metadata": {
+        "total_size": 839127488,
+        "total_parameters": 864159968
+    },
+    "weight_map": {
+        "lm_head.biases": "model.safetensors",
+        "lm_head.scales": "model.safetensors",
+        "lm_head.weight": "model.safetensors",
+        "model.embed_tokens.biases": "model.safetensors",
+        "model.embed_tokens.scales": "model.safetensors",
+        "model.embed_tokens.weight": "model.safetensors",
+        "model.layers.0.input_layernorm.weight": "model.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.1.input_layernorm.weight": "model.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.10.input_layernorm.weight": "model.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.11.input_layernorm.weight": "model.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.12.input_layernorm.weight": "model.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.13.input_layernorm.weight": "model.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.14.input_layernorm.weight": "model.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.15.input_layernorm.weight": "model.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.16.input_layernorm.weight": "model.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.17.input_layernorm.weight": "model.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.18.input_layernorm.weight": "model.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.19.input_layernorm.weight": "model.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.2.input_layernorm.weight": "model.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.20.input_layernorm.weight": "model.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.21.input_layernorm.weight": "model.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.22.input_layernorm.weight": "model.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.23.input_layernorm.weight": "model.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.24.input_layernorm.weight": "model.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.24.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.24.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.24.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.25.input_layernorm.weight": "model.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.25.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.25.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.25.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.26.input_layernorm.weight": "model.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.26.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.26.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.26.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.27.input_layernorm.weight": "model.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.27.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.27.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.27.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.28.input_layernorm.weight": "model.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.28.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.28.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.28.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.28.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.28.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.28.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.28.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.29.input_layernorm.weight": "model.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.29.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.29.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.29.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.29.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.29.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.29.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.29.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.3.input_layernorm.weight": "model.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.30.input_layernorm.weight": "model.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.30.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.30.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.30.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.30.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.30.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.30.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.30.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.31.input_layernorm.weight": "model.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.31.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.31.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.31.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.31.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.31.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.31.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.31.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.4.input_layernorm.weight": "model.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.5.input_layernorm.weight": "model.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.6.input_layernorm.weight": "model.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.7.input_layernorm.weight": "model.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.8.input_layernorm.weight": "model.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.layers.9.input_layernorm.weight": "model.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.down_proj.weight_scale": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.weight_scale": "model.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.up_proj.weight_scale": "model.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.weight_scale": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.weight_scale": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.weight_scale": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.weight_scale": "model.safetensors",
+        "model.norm.weight": "model.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,340 @@
+{
+  "additional_special_tokens": [
+    "<|pad|>",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<",
+    "<|finetune_right_pad_id|>",
+    "<|start_header_id|>",
+    "<|end_header_id|>",
+    "<|eom_id|>",
+    "<|eot_id|>",
+    "<|begin_of_text|>",
+    ">>TITLE<<",
+    "<tool_response>",
+    "</tool_response>",
+    "<tool_call>",
+    "</tool_call>",
+    "<schema>",
+    "</schema>",
+    "<scratch_pad>",
+    "</scratch_pad>",
+    "<thinking>",
+    "</thinking>",
+    "<explanation>",
+    "</explanation>",
+    "<file_sep>",
+    "<repo_name>",
+    ">>UNUSED_119<<",
+    ">>UNUSED_120<<",
+    ">>UNUSED_217<<",
+    ">>UNUSED_218<<",
+    ">>UNUSED_219<<",
+    ">>UNUSED_220<<",
+    ">>UNUSED_221<<",
+    ">>UNUSED_222<<",
+    ">>UNUSED_223<<",
+    ">>UNUSED_224<<",
+    ">>UNUSED_225<<",
+    ">>UNUSED_226<<",
+    ">>UNUSED_227<<",
+    ">>UNUSED_228<<",
+    ">>UNUSED_229<<",
+    ">>UNUSED_230<<",
+    ">>UNUSED_231<<",
+    ">>UNUSED_232<<",
+    ">>UNUSED_233<<",
+    ">>UNUSED_234<<",
+    ">>UNUSED_235<<",
+    ">>UNUSED_236<<",
+    ">>UNUSED_237<<",
+    ">>UNUSED_238<<",
+    ">>UNUSED_239<<",
+    ">>UNUSED_240<<",
+    ">>UNUSED_241<<",
+    ">>UNUSED_242<<",
+    ">>UNUSED_243<<",
+    ">>UNUSED_244<<",
+    ">>UNUSED_245<<",
+    ">>UNUSED_246<<",
+    ">>UNUSED_247<<",
+    ">>UNUSED_248<<",
+    ">>UNUSED_249<<",
+    ">>UNUSED_250<<",
+    ">>UNUSED_251<<",
+    ">>UNUSED_252<<",
+    ">>UNUSED_253<<",
+    ">>UNUSED_254<<",
+    ">>UNUSED_255<<",
+    ">>UNUSED_256<<",
+    ">>UNUSED_257<<",
+    ">>UNUSED_258<<",
+    ">>UNUSED_259<<",
+    ">>UNUSED_260<<",
+    ">>UNUSED_261<<",
+    ">>UNUSED_262<<",
+    ">>UNUSED_263<<",
+    ">>UNUSED_264<<",
+    ">>UNUSED_265<<",
+    ">>UNUSED_266<<",
+    ">>UNUSED_267<<",
+    ">>UNUSED_268<<",
+    ">>UNUSED_269<<",
+    ">>UNUSED_270<<",
+    ">>UNUSED_271<<",
+    ">>UNUSED_272<<",
+    ">>UNUSED_273<<",
+    ">>UNUSED_274<<",
+    ">>UNUSED_275<<",
+    ">>UNUSED_276<<",
+    ">>UNUSED_277<<",
+    ">>UNUSED_278<<",
+    ">>UNUSED_279<<",
+    ">>UNUSED_280<<",
+    ">>UNUSED_281<<",
+    ">>UNUSED_282<<",
+    ">>UNUSED_283<<",
+    ">>UNUSED_284<<",
+    ">>UNUSED_285<<",
+    ">>UNUSED_286<<",
+    ">>UNUSED_287<<",
+    ">>UNUSED_288<<",
+    ">>UNUSED_289<<",
+    ">>UNUSED_290<<",
+    ">>UNUSED_291<<",
+    ">>UNUSED_292<<",
+    ">>UNUSED_293<<",
+    ">>UNUSED_294<<",
+    ">>UNUSED_295<<",
+    ">>UNUSED_296<<",
+    ">>UNUSED_297<<",
+    ">>UNUSED_298<<",
+    ">>UNUSED_299<<",
+    ">>UNUSED_300<<",
+    ">>UNUSED_301<<",
+    ">>UNUSED_302<<",
+    ">>UNUSED_303<<",
+    ">>UNUSED_304<<",
+    ">>UNUSED_305<<",
+    ">>UNUSED_306<<",
+    ">>UNUSED_307<<",
+    ">>UNUSED_308<<",
+    ">>UNUSED_309<<",
+    ">>UNUSED_310<<",
+    ">>UNUSED_311<<",
+    ">>UNUSED_312<<",
+    ">>UNUSED_313<<",
+    ">>UNUSED_314<<",
+    ">>UNUSED_315<<",
+    ">>UNUSED_316<<",
+    ">>UNUSED_317<<",
+    ">>UNUSED_318<<",
+    ">>UNUSED_319<<",
+    ">>UNUSED_320<<",
+    ">>UNUSED_321<<",
+    ">>UNUSED_322<<",
+    ">>UNUSED_323<<",
+    ">>UNUSED_324<<",
+    ">>UNUSED_325<<",
+    ">>UNUSED_326<<",
+    ">>UNUSED_327<<",
+    ">>UNUSED_328<<",
+    ">>UNUSED_329<<",
+    ">>UNUSED_330<<",
+    ">>UNUSED_331<<",
+    ">>UNUSED_332<<",
+    ">>UNUSED_333<<",
+    ">>UNUSED_334<<",
+    ">>UNUSED_335<<",
+    ">>UNUSED_336<<",
+    ">>UNUSED_337<<",
+    ">>UNUSED_338<<",
+    ">>UNUSED_339<<",
+    ">>UNUSED_340<<",
+    ">>UNUSED_341<<",
+    ">>UNUSED_342<<",
+    ">>UNUSED_343<<",
+    ">>UNUSED_344<<",
+    ">>UNUSED_345<<",
+    ">>UNUSED_346<<",
+    ">>UNUSED_347<<",
+    ">>UNUSED_348<<",
+    ">>UNUSED_349<<",
+    ">>UNUSED_350<<",
+    ">>UNUSED_351<<",
+    ">>UNUSED_352<<",
+    ">>UNUSED_353<<",
+    ">>UNUSED_354<<",
+    ">>UNUSED_355<<",
+    ">>UNUSED_356<<",
+    ">>UNUSED_357<<",
+    ">>UNUSED_358<<",
+    ">>UNUSED_359<<",
+    ">>UNUSED_360<<",
+    ">>UNUSED_361<<",
+    ">>UNUSED_362<<",
+    ">>UNUSED_363<<",
+    ">>UNUSED_364<<",
+    ">>UNUSED_365<<",
+    ">>UNUSED_366<<",
+    ">>UNUSED_367<<",
+    ">>UNUSED_368<<",
+    ">>UNUSED_369<<",
+    ">>UNUSED_370<<",
+    ">>UNUSED_371<<",
+    ">>UNUSED_372<<",
+    ">>UNUSED_373<<",
+    ">>UNUSED_374<<",
+    ">>UNUSED_375<<",
+    ">>UNUSED_376<<",
+    ">>UNUSED_377<<",
+    ">>UNUSED_378<<",
+    ">>UNUSED_379<<",
+    ">>UNUSED_380<<",
+    ">>UNUSED_381<<",
+    ">>UNUSED_382<<",
+    ">>UNUSED_383<<",
+    ">>UNUSED_384<<",
+    ">>UNUSED_385<<",
+    ">>UNUSED_386<<",
+    ">>UNUSED_387<<",
+    ">>UNUSED_388<<",
+    ">>UNUSED_389<<",
+    ">>UNUSED_390<<",
+    ">>UNUSED_391<<",
+    ">>UNUSED_392<<",
+    ">>UNUSED_393<<",
+    ">>UNUSED_394<<",
+    ">>UNUSED_395<<",
+    ">>UNUSED_396<<",
+    ">>UNUSED_397<<",
+    ">>UNUSED_398<<",
+    ">>UNUSED_399<<",
+    ">>UNUSED_400<<",
+    ">>UNUSED_401<<",
+    ">>UNUSED_402<<",
+    ">>UNUSED_403<<",
+    ">>UNUSED_404<<",
+    ">>UNUSED_405<<",
+    ">>UNUSED_406<<",
+    ">>UNUSED_407<<",
+    ">>UNUSED_408<<",
+    ">>UNUSED_409<<",
+    ">>UNUSED_410<<",
+    ">>UNUSED_411<<",
+    ">>UNUSED_412<<",
+    ">>UNUSED_413<<",
+    ">>UNUSED_414<<",
+    ">>UNUSED_415<<",
+    ">>UNUSED_416<<",
+    ">>UNUSED_417<<",
+    ">>UNUSED_418<<",
+    ">>UNUSED_419<<",
+    ">>UNUSED_420<<",
+    ">>UNUSED_421<<",
+    ">>UNUSED_422<<",
+    ">>UNUSED_423<<",
+    ">>UNUSED_424<<",
+    ">>UNUSED_425<<",
+    ">>UNUSED_426<<",
+    ">>UNUSED_427<<",
+    ">>UNUSED_428<<",
+    ">>UNUSED_429<<",
+    ">>UNUSED_430<<",
+    ">>UNUSED_431<<",
+    ">>UNUSED_432<<",
+    ">>UNUSED_433<<",
+    ">>UNUSED_434<<",
+    ">>UNUSED_435<<",
+    ">>UNUSED_436<<",
+    ">>UNUSED_437<<",
+    ">>UNUSED_438<<",
+    ">>UNUSED_439<<",
+    ">>UNUSED_440<<",
+    ">>UNUSED_441<<",
+    ">>UNUSED_442<<",
+    ">>UNUSED_443<<",
+    ">>UNUSED_444<<",
+    ">>UNUSED_445<<",
+    ">>UNUSED_446<<",
+    ">>UNUSED_447<<",
+    ">>UNUSED_448<<",
+    ">>UNUSED_449<<",
+    ">>UNUSED_450<<",
+    ">>UNUSED_451<<",
+    ">>UNUSED_452<<",
+    ">>UNUSED_453<<",
+    ">>UNUSED_454<<",
+    ">>UNUSED_455<<",
+    ">>UNUSED_456<<",
+    ">>UNUSED_457<<",
+    ">>UNUSED_458<<",
+    ">>UNUSED_459<<",
+    ">>UNUSED_460<<",
+    ">>UNUSED_461<<",
+    ">>UNUSED_462<<",
+    ">>UNUSED_463<<",
+    ">>UNUSED_464<<",
+    ">>UNUSED_465<<",
+    ">>UNUSED_466<<",
+    ">>UNUSED_467<<",
+    ">>UNUSED_468<<",
+    ">>UNUSED_469<<",
+    ">>UNUSED_470<<",
+    ">>UNUSED_471<<",
+    ">>UNUSED_472<<",
+    ">>UNUSED_473<<",
+    ">>UNUSED_474<<",
+    ">>UNUSED_475<<",
+    ">>UNUSED_476<<",
+    ">>UNUSED_477<<",
+    ">>UNUSED_478<<",
+    ">>UNUSED_479<<",
+    ">>UNUSED_480<<",
+    ">>UNUSED_481<<",
+    ">>UNUSED_482<<",
+    ">>UNUSED_483<<",
+    ">>UNUSED_484<<",
+    ">>UNUSED_485<<",
+    ">>UNUSED_486<<",
+    ">>UNUSED_487<<",
+    ">>UNUSED_488<<",
+    ">>UNUSED_489<<",
+    ">>UNUSED_490<<",
+    ">>UNUSED_491<<",
+    ">>UNUSED_492<<",
+    ">>UNUSED_493<<",
+    ">>UNUSED_494<<",
+    ">>UNUSED_495<<",
+    ">>UNUSED_496<<",
+    ">>UNUSED_497<<",
+    ">>UNUSED_498<<",
+    ">>UNUSED_499<<",
+    ">>UNUSED_500<<",
+    ">>UNUSED_501<<",
+    ">>UNUSED_502<<",
+    ">>UNUSED_503<<",
+    ">>UNUSED_504<<",
+    ">>UNUSED_505<<",
+    ">>UNUSED_506<<",
+    ">>UNUSED_507<<",
+    ">>UNUSED_508<<",
+    ">>UNUSED_509<<",
+    ">>UNUSED_510<<",
+    ">>UNUSED_511<<"
+  ],
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}