Upload folder using huggingface_hub

README.md

@@ -0,0 +1,102 @@
+---
+license: bigcode-openrail-m
+library_name: transformers
+tags:
+- code
+- mlx
+base_model: bigcode/starcoder2-15b
+datasets:
+- bigcode/self-oss-instruct-sc2-exec-filter-50k
+pipeline_tag: text-generation
+model-index:
+- name: starcoder2-15b-instruct-v0.1
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: LiveCodeBench (code generation)
+      type: livecodebench-codegeneration
+    metrics:
+    - type: pass@1
+      value: 20.4
+  - task:
+      type: text-generation
+    dataset:
+      name: LiveCodeBench (self repair)
+      type: livecodebench-selfrepair
+    metrics:
+    - type: pass@1
+      value: 20.9
+  - task:
+      type: text-generation
+    dataset:
+      name: LiveCodeBench (test output prediction)
+      type: livecodebench-testoutputprediction
+    metrics:
+    - type: pass@1
+      value: 29.8
+  - task:
+      type: text-generation
+    dataset:
+      name: LiveCodeBench (code execution)
+      type: livecodebench-codeexecution
+    metrics:
+    - type: pass@1
+      value: 28.1
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEval
+      type: humaneval
+    metrics:
+    - type: pass@1
+      value: 72.6
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEval+
+      type: humanevalplus
+    metrics:
+    - type: pass@1
+      value: 63.4
+  - task:
+      type: text-generation
+    dataset:
+      name: MBPP
+      type: mbpp
+    metrics:
+    - type: pass@1
+      value: 75.2
+  - task:
+      type: text-generation
+    dataset:
+      name: MBPP+
+      type: mbppplus
+    metrics:
+    - type: pass@1
+      value: 61.2
+  - task:
+      type: text-generation
+    dataset:
+      name: DS-1000
+      type: ds-1000
+    metrics:
+    - type: pass@1
+      value: 40.6
+---
+
+# mlx-community/starcoder2-15b-instruct-v0.1
+This model was converted to MLX format from [`bigcode/starcoder2-15b-instruct-v0.1`]() using mlx-lm version **0.12.1**.
+Refer to the [original model card](https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1) 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/starcoder2-15b-instruct-v0.1")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,30 @@
+{
+    "architectures": [
+        "Starcoder2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 0,
+    "embedding_dropout": 0.0,
+    "eos_token_id": 0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 6144,
+    "initializer_range": 0.01275,
+    "intermediate_size": 24576,
+    "max_position_embeddings": 16384,
+    "mlp_type": "default",
+    "model_type": "starcoder2",
+    "norm_epsilon": 1e-05,
+    "norm_type": "layer_norm",
+    "num_attention_heads": 48,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 4,
+    "residual_dropout": 0.0,
+    "rope_theta": 100000,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.39.0.dev0",
+    "use_bias": true,
+    "use_cache": true,
+    "vocab_size": 49152
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29dd9482ad557f4c96245128ce3fe2903ac7c2f03b63c52d4a52cbc1014dec82
+size 5354251533

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5afdf3e7e5026f57b70c56aaaa51c0f8d4a366a1dc37541857be65a5960fbc
+size 5295466340

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb2cb7ef8d4101548d29291350520e6edb78872572684b070f5f89e7c98e34cf
+size 5298254997

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec7d8b5180ebf3ab58bf2cd4801d9232e967a50491b882bbbb908e604ac7a229
+size 5352157721

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5e1eaadc6e3cdb1a1c7f9ef277de716d5d490a7f827513ea116d6e4978f613
+size 5367583710

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a629efb9e93e6a27f7a75bb6a238d6915d5972fcf9c4dfd78ac832201c62ac8
+size 4362258684

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da39ea0eb7093bcc15cc7d3957e7187734901fe3021758c492781b80bb3ba8b9
+size 5367583744

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:163b6909fcefdba64760b08d00b96d343445cfcca2c811e39fdcda70716abf45
+size 1050673278

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4380fe9477e445c2ea98336c6073cfd111eeac3577e60a40e06dbf9b470bdf
+size 5298366450

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21872d39cc12bbb2a5d05c96953e669a983937c125f1a9b563a702fba6d5b5fa
+size 5071824453

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f062bf98916a98d2b40e9054373a33810ede37928730792a6f5a326f40c53202
+size 4908256518

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7412e4e5d3fd6e04559bb09a4594d3dd79bf3866eb10900083a3e6cb57050b
+size 603979900

model.safetensors.index.json

@@ -0,0 +1,651 @@
+{
+    "metadata": {
+        "total_size": 31915778048
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00007-of-00007.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.input_layernorm.bias": "model-00001-of-00007.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.0.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.input_layernorm.bias": "model-00001-of-00007.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.1.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.10.input_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
+        "model.layers.10.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.10.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.input_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
+        "model.layers.11.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.11.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.input_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
+        "model.layers.12.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.12.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.input_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.13.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.input_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+        "model.layers.14.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.14.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.input_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+        "model.layers.15.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.15.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.input_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+        "model.layers.16.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.16.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.input_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+        "model.layers.17.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.17.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.input_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+        "model.layers.18.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.18.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.input_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+        "model.layers.19.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.19.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.2.input_layernorm.bias": "model-00001-of-00007.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.2.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.20.input_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.20.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
+        "model.layers.20.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
+        "model.layers.20.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.20.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.20.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.input_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
+        "model.layers.21.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.21.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.input_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
+        "model.layers.22.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.22.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.23.input_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.23.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
+        "model.layers.23.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
+        "model.layers.23.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.23.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.23.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.24.input_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.24.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
+        "model.layers.24.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
+        "model.layers.24.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.24.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.24.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.24.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.input_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
+        "model.layers.25.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.25.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.input_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
+        "model.layers.26.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.26.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+        "model.layers.27.input_layernorm.bias": "model-00005-of-00007.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+        "model.layers.27.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.27.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.input_layernorm.bias": "model-00005-of-00007.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+        "model.layers.28.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.28.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.input_layernorm.bias": "model-00005-of-00007.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+        "model.layers.29.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.29.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.3.input_layernorm.bias": "model-00001-of-00007.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.3.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.30.input_layernorm.bias": "model-00005-of-00007.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.30.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+        "model.layers.30.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+        "model.layers.30.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.30.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.30.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.30.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.30.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.30.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.30.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.31.input_layernorm.bias": "model-00005-of-00007.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.31.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+        "model.layers.31.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+        "model.layers.31.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.31.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.31.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.31.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.31.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.31.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.31.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.32.input_layernorm.bias": "model-00005-of-00007.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.32.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+        "model.layers.32.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+        "model.layers.32.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.32.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.32.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "model.layers.32.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.32.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.32.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.32.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.33.input_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.33.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+        "model.layers.33.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+        "model.layers.33.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.33.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.33.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.33.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.33.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.33.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.33.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+        "model.layers.34.input_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
+        "model.layers.34.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.34.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.input_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
+        "model.layers.35.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.35.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.36.input_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.36.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
+        "model.layers.36.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
+        "model.layers.36.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.36.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.36.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.37.input_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.37.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
+        "model.layers.37.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
+        "model.layers.37.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.37.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.37.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.37.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.37.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.37.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.37.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.38.input_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.38.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
+        "model.layers.38.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
+        "model.layers.38.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.38.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.38.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.38.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.38.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.38.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.38.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.39.input_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.39.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
+        "model.layers.39.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
+        "model.layers.39.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.39.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.39.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "model.layers.39.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.39.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.39.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.39.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+        "model.layers.4.input_layernorm.bias": "model-00001-of-00007.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
+        "model.layers.4.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.4.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.input_layernorm.bias": "model-00001-of-00007.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
+        "model.layers.5.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.5.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.input_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.6.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+        "model.layers.7.input_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.7.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.input_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.8.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.input_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.9.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+        "model.norm.bias": "model-00006-of-00007.safetensors",
+        "model.norm.weight": "model-00006-of-00007.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,63 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,357 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<repo_name>",
+    "<file_sep>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>",
+    "<code_to_intermediate>",
+    "<intermediate_to_code>",
+    "<pr>",
+    "<pr_status>",
+    "<pr_is_merged>",
+    "<pr_base>",
+    "<pr_file>",
+    "<pr_base_code>",
+    "<pr_diff>",
+    "<pr_diff_hunk>",
+    "<pr_comment>",
+    "<pr_event_id>",
+    "<pr_review>",
+    "<pr_review_state>",
+    "<pr_review_comment>",
+    "<pr_in_reply_to_review_id>",
+    "<pr_in_reply_to_comment_id>",
+    "<pr_diff_hunk_comment_line>",
+    "<NAME>",
+    "<EMAIL>",
+    "<KEY>",
+    "<PASSWORD>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{{bos_token}}{{'You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.\n\n'}}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n        {{ raise_exception('System messages are not allowed in this template.') }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction\n' + message['content'] + '\n\n'}}\n        {%- else %}\n{{'### Response\n' + message['content'] + eos_token + '\n\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{{'### Response\n'}}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}