Upload folder using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+base_model:
+- WizardLMTeam/WizardCoder-33B-V1.1
+- deepseek-ai/deepseek-coder-33b-instruct
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [WizardLMTeam/WizardCoder-33B-V1.1](https://huggingface.co/WizardLMTeam/WizardCoder-33B-V1.1)
+* [deepseek-ai/deepseek-coder-33b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+- sources:
+  - model: deepseek-ai/deepseek-coder-33b-instruct
+    layer_range:
+    - 0
+    - 32
+  - model: WizardLMTeam/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
+```

config.json

@@ -0,0 +1,34 @@
+{
+  "_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,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 19200,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "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,
+    "rope_type": "linear",
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 32256
+}

mergekit_config.yml

@@ -0,0 +1,30 @@
+slices:
+- sources:
+  - model: deepseek-ai/deepseek-coder-33b-instruct
+    layer_range:
+    - 0
+    - 32
+  - model: WizardLMTeam/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-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8630ba54d0bc8a017f4e41eaff676fbba7e5cd7a6f9abd079b7778e0187cb66e
+size 4947300312

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e30e74bb5d242354267b0eba473dc6326d4e7ecfddb1ec7b992b5efa077d9796
+size 4738124488

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b976e459941fc91154241ae5f53f383a8a70e95ef9b8d712195fa4b1865ef0ca
+size 4910615232

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046fe1b72eb9c3ae3e4e65bd328eb02fe15adadf5f2ca83908ab1d6ca7529771
+size 4910615232

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab1b6243a6832249356373b2f8bd93384630329ab67ba2f38ea071289cabb68
+size 4752819120

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d49c840158206582384edf18ea148d1d572655a92737be5e7ef0d9943dc6d58
+size 4793160032

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09123a57749e6ca40fb99f87126fe3d28baabf4c333fe4ae8157569e50003da8
+size 4752819080

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f84f9cb23071fe842a082ed8bc17c36455d352043b5cec059fb13d2859a628
+size 1060664344

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 34866083840}, "weight_map": {"lm_head.weight": "model-00001-of-00008.safetensors", "model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.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 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+}