Upload folder using huggingface_hub

README.md

@@ -1,3 +1,55 @@
 ---
-license: apache-2.0
+base_model:
+- deepseek-ai/deepseek-coder-6.7b-instruct
+- m-a-p/OpenCodeInterpreter-DS-6.7B
+- deepseek-ai/deepseek-coder-6.7b-base
+library_name: transformers
+tags:
+- mergekit
+- merge
+
 ---
+# output-model-directory
+
+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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct)
+* [m-a-p/OpenCodeInterpreter-DS-6.7B](https://huggingface.co/m-a-p/OpenCodeInterpreter-DS-6.7B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: deepseek-ai/deepseek-coder-6.7b-instruct
+    parameters:
+      density: [1, 0.7, 0.1] # density gradient
+      weight: 1.0
+  - model: m-a-p/OpenCodeInterpreter-DS-6.7B
+    parameters:
+      density: 0.5
+      weight: [0, 0.3, 0.7, 1] # weight gradient
+ # - model: NousResearch/Nous-Hermes-llama-2-7b
+  #  parameters:
+   #   density: 0.33
+    #  weight:
+     #   - filter: mlp
+      #    value: 0.5
+       # - value: 0
+merge_method: ties
+base_model: deepseek-ai/deepseek-coder-6.7b-base
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: float16
+
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-coder-6.7b-base",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32256
+}

mergekit_config.yml

@@ -0,0 +1,22 @@
+models:
+  - model: deepseek-ai/deepseek-coder-6.7b-instruct
+    parameters:
+      density: [1, 0.7, 0.1] # density gradient
+      weight: 1.0
+  - model: m-a-p/OpenCodeInterpreter-DS-6.7B
+    parameters:
+      density: 0.5
+      weight: [0, 0.3, 0.7, 1] # weight gradient
+ # - model: NousResearch/Nous-Hermes-llama-2-7b
+  #  parameters:
+   #   density: 0.33
+    #  weight:
+     #   - filter: mlp
+      #    value: 0.5
+       # - value: 0
+merge_method: ties
+base_model: deepseek-ai/deepseek-coder-6.7b-base
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: float16

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c79f746edb95ca9014f78455ea2fd3cde9d1e8d2e26e969917260135aac72d
+size 1990275952

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffb5cd37370745c81438f5b90f1505c4eb30a32ad746bcd0ffbf2967e1c7f78c
+size 1990284256

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3920841828c17ac992733ed443499fb3c6956b0c0bb27569d7d1af0915329303
+size 1990284240

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0528342127487ee9ab8aaec6abfc25eec1e74f33257872fb0ae18ec6508562dd
+size 1990284208

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32ee80efced857a211537cdae0910b31206ece4fbb45806af0a011568809ade
+size 1753297488

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e5e6501cdb311d483184e042065e69d830ba288bb62168d0d34b1a69796242a
+size 1923149384

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2e04aaecbd4e8c5f8776a3dc0d71dcabb59cc14256d1541319dfc12e3f374b
+size 1843483488

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.23.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.embed_tokens.weight": "model-00006-of-00007.safetensors", "lm_head.weight": "model-00006-of-00007.safetensors", "model.norm.weight": "model-00006-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00007.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": "<｜end▁of▁sentence｜>",
+    "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 +1,192 @@
+{
+  "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": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "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
+}