Upload folder using huggingface_hub (#1)

- 0c22ab6f616e7ee18e340999317196512cabab4c68ccf0174c551ab20aab8bf1 (1e0317063e561f9785c997df1e3718d390664153)
- ad3ad9196d9e27b1739a331a9c750799aa4b2eb452a6af1426bdbaffab6d1359 (4c84f379f2a5ba3743121cbfb85c1c1160e6482c)

README.md

@@ -0,0 +1,57 @@
+---
+license: apache-2.0
+widget:
+- example_title: Yi-34B-Chat
+  text: hi
+  output:
+    text: ' Hello! How can I assist you today?'
+- example_title: Yi-34B
+  text: There's a place where time stands still. A place of breath taking wonder,
+    but also
+  output:
+    text: ' an eerie sense that something is just not right…
+
+      Between the two worlds lies The Forgotten Kingdom - home to creatures long since
+      thought extinct and ancient magic so strong it defies belief! Only here can
+      you find what has been lost for centuries: An Elixir Of Life which will restore
+      youth and vitality if only those who seek its power are brave enough to face
+      up against all manner of dangers lurking in this mysterious land! But beware;
+      some say there may even exist powerful entities beyond our comprehension whose
+      intentions towards humanity remain unclear at best ---- they might want nothing
+      more than destruction itself rather then anything else from their quest after
+      immortality (and maybe someone should tell them about modern medicine)? In any
+      event though – one thing remains true regardless : whether or not success comes
+      easy depends entirely upon how much effort we put into conquering whatever challenges
+      lie ahead along with having faith deep down inside ourselves too ;) So let’s
+      get started now shall We?'
+pipeline_tag: text-generation
+tags:
+- mlx
+base_model: 01-ai/Yi-6B-Chat
+---
+
+# mlx-community/Yi-6B-Chat-8bit
+
+The Model [mlx-community/Yi-6B-Chat-8bit](https://huggingface.co/mlx-community/Yi-6B-Chat-8bit) was converted to MLX format from [01-ai/Yi-6B-Chat](https://huggingface.co/01-ai/Yi-6B-Chat) using mlx-lm version **0.19.2**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Yi-6B-Chat-8bit")
+
+prompt="hello"
+
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

config.json

@@ -0,0 +1,34 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 4096,
+    "model_type": "llama",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "pretraining_tp": 1,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 5000000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.35.0",
+    "use_cache": true,
+    "vocab_size": 64000
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc39cd396f0ee2a091339aa5a9307764cdc6c2b8ec0343fa15d7401cff0cd41
+size 5330426718

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3203aaf656cb682bc2d79b28fa22e7eef5dcf8c088b4944d8ccf9958fea239e0
+size 1109757297

model.safetensors.index.json

@@ -0,0 +1,750 @@
+{
+    "metadata": {
+        "total_size": 6440099840
+    },
+    "weight_map": {
+        "lm_head.biases": "model-00002-of-00002.safetensors",
+        "lm_head.scales": "model-00002-of-00002.safetensors",
+        "lm_head.weight": "model-00002-of-00002.safetensors",
+        "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
+        "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.norm.weight": "model-00002-of-00002.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|im_sep|>"
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,1873 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<|im_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<h1/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<h2/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "38": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "39": {
+      "content": "<h3/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "40": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "41": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "42": {
+      "content": "<h4/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "43": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "44": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "45": {
+      "content": "<h5/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "47": {
+      "content": "<br>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "48": {
+      "content": "<br/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49": {
+      "content": "</br>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51": {
+      "content": "<strong/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "53": {
+      "content": "<p>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "54": {
+      "content": "<p/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "55": {
+      "content": "</p>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "56": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57": {
+      "content": "<table/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "59": {
+      "content": "<li>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "60": {
+      "content": "<li/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61": {
+      "content": "</li>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "62": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "63": {
+      "content": "<tr/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "content": "<tbody/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "67": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "68": {
+      "content": "<img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "69": {
+      "content": "<img/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "70": {
+      "content": "</img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "71": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "72": {
+      "content": "<b/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "73": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "74": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75": {
+      "content": "<td/>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "76": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "115": {
+      "content": "<!--",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "118": {
+      "content": "<!DOCTYPE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "145": {
+      "content": "<|unused000|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "146": {
+      "content": "<|unused001|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "147": {
+      "content": "<|unused002|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "148": {
+      "content": "<|unused003|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "149": {
+      "content": "<|unused004|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "150": {
+      "content": "<|unused005|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151": {
+      "content": "<|unused006|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "152": {
+      "content": "<|unused007|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "153": {
+      "content": "<|unused008|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "154": {
+      "content": "<|unused009|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "155": {
+      "content": "<|unused010|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "156": {
+      "content": "<|unused011|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "157": {
+      "content": "<|unused012|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "158": {
+      "content": "<|unused013|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "159": {
+      "content": "<|unused014|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "160": {
+      "content": "<|unused015|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "161": {
+      "content": "<|unused016|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "162": {
+      "content": "<|unused017|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "163": {
+      "content": "<|unused018|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "164": {
+      "content": "<|unused019|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "165": {
+      "content": "<|unused020|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166": {
+      "content": "<|unused021|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "167": {
+      "content": "<|unused022|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "168": {
+      "content": "<|unused023|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "169": {
+      "content": "<|unused024|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "170": {
+      "content": "<|unused025|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "171": {
+      "content": "<|unused026|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "172": {
+      "content": "<|unused027|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "173": {
+      "content": "<|unused028|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "174": {
+      "content": "<|unused029|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "175": {
+      "content": "<|unused030|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "176": {
+      "content": "<|unused031|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "177": {
+      "content": "<|unused032|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "178": {
+      "content": "<|unused033|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "179": {
+      "content": "<|unused034|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "180": {
+      "content": "<|unused035|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "181": {
+      "content": "<|unused036|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "182": {
+      "content": "<|unused037|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "183": {
+      "content": "<|unused038|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "184": {
+      "content": "<|unused039|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "185": {
+      "content": "<|unused040|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "186": {
+      "content": "<|unused041|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "187": {
+      "content": "<|unused042|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "188": {
+      "content": "<|unused043|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "189": {
+      "content": "<|unused044|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "190": {
+      "content": "<|unused045|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "191": {
+      "content": "<|unused046|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "192": {
+      "content": "<|unused047|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "193": {
+      "content": "<|unused048|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "194": {
+      "content": "<|unused049|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "195": {
+      "content": "<|unused050|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "196": {
+      "content": "<|unused051|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "197": {
+      "content": "<|unused052|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "198": {
+      "content": "<|unused053|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "199": {
+      "content": "<|unused054|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200": {
+      "content": "<|unused055|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "201": {
+      "content": "<|unused056|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "202": {
+      "content": "<|unused057|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "203": {
+      "content": "<|unused058|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "204": {
+      "content": "<|unused059|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "205": {
+      "content": "<|unused060|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "206": {
+      "content": "<|unused061|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "207": {
+      "content": "<|unused062|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "208": {
+      "content": "<|unused063|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "209": {
+      "content": "<|unused064|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "210": {
+      "content": "<|unused065|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "211": {
+      "content": "<|unused066|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "212": {
+      "content": "<|unused067|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "213": {
+      "content": "<|unused068|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "214": {
+      "content": "<|unused069|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "215": {
+      "content": "<|unused070|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "216": {
+      "content": "<|unused071|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "217": {
+      "content": "<|unused072|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "218": {
+      "content": "<|unused073|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "219": {
+      "content": "<|unused074|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "220": {
+      "content": "<|unused075|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "221": {
+      "content": "<|unused076|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "222": {
+      "content": "<|unused077|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "223": {
+      "content": "<|unused078|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "224": {
+      "content": "<|unused079|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "225": {
+      "content": "<|unused080|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "226": {
+      "content": "<|unused081|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "227": {
+      "content": "<|unused082|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "228": {
+      "content": "<|unused083|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "229": {
+      "content": "<|unused084|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "230": {
+      "content": "<|unused085|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "231": {
+      "content": "<|unused086|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "232": {
+      "content": "<|unused087|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "233": {
+      "content": "<|unused088|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "234": {
+      "content": "<|unused089|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "235": {
+      "content": "<|unused090|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "236": {
+      "content": "<|unused091|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "237": {
+      "content": "<|unused092|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "238": {
+      "content": "<|unused093|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "239": {
+      "content": "<|unused094|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "240": {
+      "content": "<|unused095|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "241": {
+      "content": "<|unused096|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "242": {
+      "content": "<|unused097|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "243": {
+      "content": "<|unused098|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "244": {
+      "content": "<|unused099|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "245": {
+      "content": "<|unused100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "246": {
+      "content": "<|unused101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "247": {
+      "content": "<|unused102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "248": {
+      "content": "<|unused103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "249": {
+      "content": "<|unused104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250": {
+      "content": "<|unused105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "251": {
+      "content": "<|unused106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "252": {
+      "content": "<|unused107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "253": {
+      "content": "<|unused108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "254": {
+      "content": "<|unused109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255": {
+      "content": "<|unused110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "256": {
+      "content": "<|unused111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "257": {
+      "content": "<|unused112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "258": {
+      "content": "<|unused113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "259": {
+      "content": "<|unused114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "260": {
+      "content": "<|unused115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "261": {
+      "content": "<|unused116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "262": {
+      "content": "<|unused117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "263": {
+      "content": "<|unused118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "264": {
+      "content": "<|unused119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "265": {
+      "content": "<|unused120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "266": {
+      "content": "<|unused121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "267": {
+      "content": "<|unused122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "268": {
+      "content": "<|unused123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "269": {
+      "content": "<|unused124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "270": {
+      "content": "<|unused125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "271": {
+      "content": "<|unused126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "272": {
+      "content": "<|unused127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "273": {
+      "content": "<|unused128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "274": {
+      "content": "<|unused129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "275": {
+      "content": "<|unused130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "276": {
+      "content": "<|unused131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "277": {
+      "content": "<|unused132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "278": {
+      "content": "<|unused133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "279": {
+      "content": "<|unused134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "280": {
+      "content": "<|unused135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "281": {
+      "content": "<|unused136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "282": {
+      "content": "<|unused137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "283": {
+      "content": "<|unused138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "284": {
+      "content": "<|unused139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "285": {
+      "content": "<|unused140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "286": {
+      "content": "<|unused141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "287": {
+      "content": "<|unused142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "288": {
+      "content": "<|unused143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "289": {
+      "content": "<|unused144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "290": {
+      "content": "<|unused145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "291": {
+      "content": "<|unused146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "292": {
+      "content": "<|unused147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "293": {
+      "content": "<|unused148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "294": {
+      "content": "<|unused149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "295": {
+      "content": "<|unused150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "296": {
+      "content": "<|unused151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "297": {
+      "content": "<|unused152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "298": {
+      "content": "<|unused153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "299": {
+      "content": "<|unused154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "300": {
+      "content": "<|unused155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "301": {
+      "content": "<|unused156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "302": {
+      "content": "<|unused157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "303": {
+      "content": "<|unused158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "304": {
+      "content": "<|unused159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|im_sep|>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}