Upload folder using huggingface_hub

README.md

@@ -0,0 +1,34 @@
+---
+language:
+- en
+license: mit
+tags:
+- convAI
+- conversational
+- mlx
+license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE
+widget:
+- text: Hello who are you?
+  example_title: Identity
+- text: What can you do?
+  example_title: Capabilities
+- text: Create a fastapi endpoint to retrieve the weather given a zip code.
+  example_title: Coding
+pipeline_tag: text-generation
+---
+
+# mitkox/phi-2-super-OpenHermes-2.5-moe-mlx
+This model was converted to MLX format from [`abacaj/phi-2-super`]().
+Refer to the [original model card](https://huggingface.co/abacaj/phi-2-super) for more details on the model.
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mitkox/phi-2-super-OpenHermes-2.5-moe-mlx")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

config.json

@@ -0,0 +1,88 @@
+{
+    "vocab_size": 51200,
+    "hidden_size": 2560,
+    "intermediate_size": 10240,
+    "num_hidden_layers": 32,
+    "num_attention_heads": 32,
+    "num_key_value_heads": 32,
+    "resid_pdrop": 0.1,
+    "embd_pdrop": 0.0,
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_new",
+    "max_position_embeddings": 2048,
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-05,
+    "use_cache": true,
+    "rope_theta": 10000.0,
+    "rope_scaling": null,
+    "partial_rotary_factor": 0.4,
+    "qk_layernorm": false,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": "bfloat16",
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": false,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+        "PhiForCausalLM"
+    ],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 50256,
+    "pad_token_id": null,
+    "eos_token_id": 50256,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "/Users/mitko/.cache/huggingface/hub/models--abacaj--phi-2-super/snapshots/f1e578c868e6cc20fb1ea8eeee427ddf6e0e2ee4",
+    "transformers_version": "4.38.1",
+    "auto_map": {
+        "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+        "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+    },
+    "model_type": "phi"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c66d47e8b51a6caef7a358530e6407b00eb1a7b40f9d5b161707a98c646a7e8
+size 5297171197

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:081765040ea7d60991697a09492747dc9696ddb2878b36be7836de75507b46a2
+size 262246604

model.safetensors.index.json

@@ -0,0 +1,460 @@
+{
+    "metadata": {
+        "total_size": 5559367680
+    },
+    "weight_map": {
+        "lm_head.bias": "model-00002-of-00002.safetensors",
+        "lm_head.weight": "model-00002-of-00002.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "model.final_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.final_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.30.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.30.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.31.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.31.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "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.bias": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,325 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}