Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- deepseek-ai/deepseek-coder-33b-instruct
+- WizardLM/WizardCoder-33B-V1.1
+base_model:
+- deepseek-ai/deepseek-coder-33b-instruct
+- WizardLM/WizardCoder-33B-V1.1
+---
+
+# Deepseek-Wizard-33B-slerp
+
+Deepseek-Wizard-33B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [deepseek-ai/deepseek-coder-33b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct)
+* [WizardLM/WizardCoder-33B-V1.1](https://huggingface.co/WizardLM/WizardCoder-33B-V1.1)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: deepseek-ai/deepseek-coder-33b-instruct
+        layer_range: [0, 32]
+      - model: WizardLM/WizardCoder-33B-V1.1
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: deepseek-ai/deepseek-coder-33b-instruct
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "arvind22/Deepseek-Wizard-33B-slerp"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+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 +1,31 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-coder-33b-instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 19200,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32256
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: deepseek-ai/deepseek-coder-33b-instruct
+        layer_range: [0, 32]
+      - model: WizardLM/WizardCoder-33B-V1.1
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: deepseek-ai/deepseek-coder-33b-instruct
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b64b797307647fdd2065e62f328191d0842932edc9854becdb12a53478814f
+size 1846048488

model-00002-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:381ea1f01d06b7253c859eb54b7ab7167ebad6cf94e7e35365abb5fb6550db9d
+size 1846077384

model-00003-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26697961addc76ed19b4b2bc4b94c6753247a96e04bcc4dc9d082bc0c17221c9
+size 1930458728

model-00004-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3049a3f42091ba61814195e0e26c17d57109a8bddc927f1e6f0c23e5c0f7e122
+size 1989193328

model-00005-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6994c3514cc549eec706a4d18d5cf76fb56d1055f3d727e3f05d06793d42ccd4
+size 1846062936

model-00006-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b54e139e097dd3c1bfb0b786c7bde3f7afa1e63b7cec36a97385ff0aecc3cda2
+size 1846077400

model-00007-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e0dbbac4f07120b022a34526836eb0da81cb44a9a053e16896a18144895ce7f
+size 1846077392

model-00008-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74bc612a67e349a792ac9689aba40891e1f12cb5911340f0aae0a7031422fe86
+size 1989207776

model-00009-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f3730ac05459e11dccd4ea3ee04c6cbd9816a180aa71fedc7c5e940f2964e0
+size 1743287936

model-00010-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bcd0fc6a4e06805d7f101d5202c6a6e9dd1f1c545c89fbe381e0dffc56bb655
+size 1846077408

model-00011-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9168f9b327c4f7ea416b8322b4184518afef756675703a746937bc380dc41fe7
+size 1846077392

model-00012-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b362879527a9a239ddd01bdf6c94ba29464bc452c23efd13efbad45e6341df77
+size 1989193336

model-00013-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbdaee1247fe03e1c9c1a57076f58e3eced6fa4c58cc8fbe6c47c83b1cd6652d
+size 1743331280

model-00014-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ad866621a3f81a190230f5122ce15bf0937526fbe923fc4c01c184d68e3550
+size 1846048496

model-00015-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db2438fdda2a72a68d0fd6b53d652b3c81d39ee2dd9da3492fa13bef737ca96
+size 1846077392

model-00016-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ed0ccd88b880b58dd18d44aec0f790750a31a0edbf434f6727d39c5f8e039d
+size 1989193336

model-00017-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85c5ee7ed0f8695f7aea26619999fe3d8fb8152b4be51b687d56e49db75fa6c7
+size 1743302384

model-00018-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67203e1bf0c5e5a22925e9ff27ffba8fa0020fcbeac889feb364364ebdcec108
+size 1846106296

model-00019-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4842961487b71a60d948344810a89f0c5246747c59d5825a62b5a077bc27354
+size 1288219416

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 34866083840}, "weight_map": {"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00019.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00019.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00019.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00019.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00019.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00019.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00019.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00019.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00019.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00019.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00019.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00019.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00019.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00019.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00019.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00019.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00019.safetensors", "model.embed_tokens.weight": "model-00003-of-00019.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00019.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00019.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00019.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00019.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00019.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00019.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00019.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00019.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00019.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00019.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00019.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00019.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00019.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00005-of-00019.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00019.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00019.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00019.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00019.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00019.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00019.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00019.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00019.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00019.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00019.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00019.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00019.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00019.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00019.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00019.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.11.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00007-of-00019.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00019.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00007-of-00019.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00019.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00019.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00019.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00019.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00019.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00019.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00019.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00019.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00008-of-00019.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00019.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00019.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00019.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00019.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00009-of-00019.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00019.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00019.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00019.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00019.safetensors", "model.layers.16.input_layernorm.weight": "model-00009-of-00019.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00009-of-00019.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00019.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.15.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00010-of-00019.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00010-of-00019.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00010-of-00019.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00010-of-00019.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00019.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00019.safetensors", "model.layers.14.input_layernorm.weight": "model-00010-of-00019.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00010-of-00019.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.13.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00011-of-00019.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00019.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00011-of-00019.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00019.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00019.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00019.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00019.safetensors", "model.layers.21.input_layernorm.weight": "model-00011-of-00019.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00019.safetensors", "model.layers.20.input_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00012-of-00019.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00019.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00012-of-00019.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00019.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00019.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.19.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00013-of-00019.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00019.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00019.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00019.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00013-of-00019.safetensors", "model.layers.18.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00013-of-00019.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.17.input_layernorm.weight": "model-00013-of-00019.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00019.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00014-of-00019.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00014-of-00019.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00019.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00019.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00019.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00019.safetensors", "model.layers.25.input_layernorm.weight": "model-00014-of-00019.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00014-of-00019.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00015-of-00019.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00019.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00019.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00019.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00019.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00019.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00019.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00019.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.22.input_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00019.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00019.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00016-of-00019.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00019.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00016-of-00019.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00016-of-00019.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00016-of-00019.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.30.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00017-of-00019.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00017-of-00019.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00017-of-00019.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00017-of-00019.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00017-of-00019.safetensors", "model.layers.29.input_layernorm.weight": "model-00017-of-00019.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00017-of-00019.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00017-of-00019.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.28.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00018-of-00019.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00018-of-00019.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00019.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00019.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00019.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00019.safetensors", "model.layers.27.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00018-of-00019.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.26.input_layernorm.weight": "model-00018-of-00019.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00019-of-00019.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00019.safetensors", "model.layers.31.input_layernorm.weight": "model-00019-of-00019.safetensors", "lm_head.weight": "model-00019-of-00019.safetensors", "model.norm.weight": "model-00019-of-00019.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,193 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set ns.found = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}