Upload folder using huggingface_hub

README.md

@@ -0,0 +1,133 @@
+---
+language:
+- en
+license: other
+tags:
+- mlx
+datasets:
+- ehartford/dolphin
+- jondurbin/airoboros-2.2.1
+- ehartford/samantha-data
+- ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
+license_name: yi-license
+license_link: LICENSE
+model-index:
+- name: dolphin-2.2-yi-34b-200k
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 42.15
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 68.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 55.47
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 45.93
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 3.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ehartford/dolphin-2.2-yi-34b-200k
+      name: Open LLM Leaderboard
+---
+
+# mlx-community/dolphin-2.2-yi-34b-200k
+This model was converted to MLX format from [`cognitivecomputations/dolphin-2.2-yi-34b-200k`]() using mlx-lm version **0.7.0**.
+Refer to the [original model card](https://huggingface.co/cognitivecomputations/dolphin-2.2-yi-34b-200k) for more details on the model.
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/dolphin-2.2-yi-34b-200k")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,81 @@
+{
+    "add_cross_attention": false,
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 7,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 7168,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 20480,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 200000,
+    "min_length": 0,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 56,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 60,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 5000000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.39.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 64000
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2feb8ac23d0d8abaf9b9725546bfc78446c76ef7e6af89684a53f4b273c057d4
+size 5086732109

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfd0d9d07c3529b6f96c14736ae1495323cace7d006d7ba66e709d7b2d2930ed
+size 5284971467

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d057f139ea59098e60e50fa93e75f40ed06fb6abfee75b64d9fd139264771b3
+size 5284971490

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff23c04b7906ae44ee74a8a24c875d57ee123aac977cff7094a97560c4101822
+size 5343691410

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae50a76eb8af5c45cbc704b71578a9710f61b298f1ab84bb1dd86aee768bb5e9
+size 5284942606

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7688a2775bc34ff2eb0cf4a31b6872551802b82a625c998ad8d1fb1bbc47dba5
+size 5284971515

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d97107e842e6dd930f3c24ddb6f4a70a42bb3a8d9740b523830aebce7b5c50e
+size 5284971507

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593ccdac7d94192bbb697541870683108d34e64ceba3e50752fc61a342042316
+size 5343691422

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb13bf09a45f8d1f0284dfb00012031be7e58035b427cf9040ab12d03053fe13
+size 5284942610

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2692f4b04ed03af2bf655edee6983ac38049b696f9751858513740a9c1a66044
+size 5284971503

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0daff2cb6c993fe8bbaf816ec13922eb1adfae034f23d8e4bd1725440e2809c9
+size 5284971503

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d2bdfddde38c766884ac05dd8c8beabdf31195e701552d2217aaf3ee047ca84
+size 5343691420

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127a45cab906baf5ee582f9bf06077392c4b5333328be10bea43f7b4d11632d2
+size 4462872726

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e892c9cd1887a50b4389f55de11084f1b826e649ea4e60549a2530ddd91af76
+size 917504124

model.safetensors.index.json

@@ -0,0 +1,550 @@
+{
+    "metadata": {
+        "total_size": 68777834496
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00014-of-00014.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.51.input_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.51.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.51.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.51.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.51.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.52.input_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.52.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.52.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.56.input_layernorm.weight": "model-00013-of-00014.safetensors",
+        "model.layers.56.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.56.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.56.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.56.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+        "model.layers.56.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.56.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.56.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.57.input_layernorm.weight": "model-00013-of-00014.safetensors",
+        "model.layers.57.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.57.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.57.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+        "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+        "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.58.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+        "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+        "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+        "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+        "model.norm.weight": "model-00013-of-00014.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "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 +1,57 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 200000,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}