Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- deepseek-ai/deepseek-coder-6.7b-instruct
+- defog/sqlcoder-7b-2
+base_model:
+- deepseek-ai/deepseek-coder-6.7b-instruct
+- defog/sqlcoder-7b-2
+---
+
+# DevPearl-2x7B
+
+DevPearl-2x7B is a Mixure of Experts (MoE) made with the following models :
+* [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct)
+* [defog/sqlcoder-7b-2](https://huggingface.co/defog/sqlcoder-7b-2)
+
+## Configuration
+
+```yaml
+base_model: codellama/CodeLlama-7b-Instruct-hf
+experts:
+  - source_model: deepseek-ai/deepseek-coder-6.7b-instruct
+    positive_prompts:
+      - "python"
+      - "javascript"
+      - "java"
+  - source_model: defog/sqlcoder-7b-2
+    positive_prompts:
+      - "SQL"
+```
+
+## Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "louisbrulenaudet/DevPearl-2x7B"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
+prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32016
+}

mergekit_moe_config.yml

@@ -0,0 +1,11 @@
+
+base_model: codellama/CodeLlama-7b-Instruct-hf
+experts:
+  - source_model: deepseek-ai/deepseek-coder-6.7b-instruct
+    positive_prompts:
+      - "python"
+      - "javascript"
+      - "java"
+  - source_model: defog/sqlcoder-7b-2
+    positive_prompts:
+      - "SQL"

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c8cfd30cb39dc40e86461f7687a0c20db266aabd73eeb01aad6a9a078112ee
+size 1967667016

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22804e6a05ad508e9eef0fca1f80e2b689f857e2ba13f18df6a3d99b2093ce01
+size 1983908704

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aca9953073faeb0250ecb66742f3498651e11de935cf325c792f314b2bb2b9f
+size 1983908704

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a586bbb06748c4cf5997ee0e55f99a574b23a17b2867aa9fa1725d5c13755aaa
+size 1983908688

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e68285c2b2f3edc5e3d7c3aa0f35c036e239628f36bab7c84db1766e4f0ef46a
+size 1983908704

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b95f1732c8ecc1ced3088f5a3676c848e19b7af7ae9e62b3f86d288ed773c60d
+size 1983908704

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c87c000da61aace77724d31e05dece4f1f349946a596717fa832505dd6a9976
+size 1983908688

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a1087589f1b1c24fd9168232c42ef3d26cd81ba668c45a28279bb699b8cbdd
+size 1983908704

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60445a104a01284bbdafd713facf3222f175f0154fcdfe195c9e572161048502
+size 1984174568

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29fa5b13ac6b4a4062830b62f4210942a12da958169bb041d23b5878b1e847e6
+size 1979718400

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0603f095a392df414d34e59f43a5478f5d80d9059a80ad0b4a469df5fb7957
+size 1979718400

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09ee576ca1a4edfb3d5b22b9ec4309c74a42347efe998bfc45c3ce3bf6c7225
+size 336073456

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00012.safetensors", "model.norm.weight": "model-00001-of-00012.safetensors", "lm_head.weight": "model-00001-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00012-of-00012.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": "<s>",
+  "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 sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "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
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}