Model save

README.md

@@ -0,0 +1,69 @@
+---
+license: llama2
+base_model: codellama/CodeLlama-34b-Instruct-hf
+tags:
+- trl
+- sft
+- unsloth
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: CodeLlama-34b-Instruct-Shader-hf
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# CodeLlama-34b-Instruct-Shader-hf
+
+This model is a fine-tuned version of [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7792
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0025
+- train_batch_size: 4
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: polynomial
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.3476        | 0.25  | 1000 | 1.3561          |
+| 1.3274        | 0.49  | 2000 | 1.1683          |
+| 1.1964        | 0.74  | 3000 | 1.0129          |
+| 0.8117        | 0.98  | 4000 | 0.9106          |
+| 0.5179        | 1.23  | 5000 | 0.8560          |
+| 0.7726        | 1.48  | 6000 | 0.8096          |
+| 0.7396        | 1.72  | 7000 | 0.7855          |
+| 0.6125        | 1.97  | 8000 | 0.7792          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1
+- Datasets 2.18.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "▁<EOT>": 32003,
+  "▁<MID>": 32001,
+  "▁<PRE>": 32000,
+  "▁<SUF>": 32002
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "codellama/CodeLlama-34b-Instruct-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "unsloth_version": "2024.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:679949bfffd2f9623f633940999081f545a0edde4e72cd0311921a13dea48b08
+size 4978740880

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3e10b53fc5a5720dcc695e88701bb36d2d71762bc2363e8a18c0f1089325e5
+size 4873882928

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1689fe8677db9a3432cd5cf89b2bf89ad2479f915604b552352d29c475c1b80
+size 4815196024

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee8b309dbd65e7d6e87e46c1ecb2e39b102254c9304ce7b31f85422e57ada8ba
+size 4873882952

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7f94835f32247b9a492ba1d02d67ca6cca05a5fb2cedf3b9ce1900366505f9
+size 4815196056

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f6169284f5fe81ab23accfa0125153c25a94cded2f660030118f58aebc75162
+size 4873882952

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad40e10bfa40896b79a7ff3e3a6380f8a6bde26a7dd020b162fed68e195ced9
+size 4815196056

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc715d3442c978e90a70fe4c83909f473c6d2ee150257daf689fcf791a06c3f4
+size 4873882952

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054b1b0621bb7a14b2bd53c1599878340b8642c5e81122bbcf59ecbaed5f1959
+size 4815196056

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54414757f8da5530b13b420fac33e8fcff6324aa05d6f21db269da7ec1da95ac
+size 4873882952

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88f48912b3a7557533dd8b9a875f1f5768f6085d19e6f261b51e8713cd08b600
+size 4815196056

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7992ffad70d218e62473e74917c04e4f7703864edb9ece8bbe0832b98539f41
+size 4873882952

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1d3d7b3a69e0024406617ca43f291af99a517cd3746bd10806dcb2e851657b
+size 4815196056

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31abd9dd902c298393d9a33a6cbb0fa107d6d9e638c3ae75c80f65df1dc6c01b
+size 4374776656

model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 67487940608
+  },
+  "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-00004-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-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-00004-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-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-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-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-00007-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-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-00009-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00012-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-00012-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00014-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.6.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-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-00003-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-00003-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-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-00003-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-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-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-00014-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,85 @@
+{
+  "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": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 16384,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b448effbbb60dd88900eaecd64b4901a878da37126d481ba1c09eef9d68e758c
+size 5048