Upload folder using huggingface_hub

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,53 @@
+---
+base_model:
+- beomi/llama-2-ko-7b
+- defog/sqlcoder-7b-2
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# sqlcoder-7b-2-slerp
+
+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:
+* [beomi/llama-2-ko-7b](https://huggingface.co/beomi/llama-2-ko-7b)
+* [defog/sqlcoder-7b-2](https://huggingface.co/defog/sqlcoder-7b-2)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model:
+  model:
+    path: defog/sqlcoder-7b-2
+dtype: float16
+merge_method: slerp
+parameters:
+  t:
+  - filter: self_attn
+    value: [0.0, 0.5, 0.3, 0.7, 1.0]
+  - filter: mlp
+    value: [1.0, 0.5, 0.7, 0.3, 0.0]
+  - value: 0.5
+slices:
+- sources:
+  - layer_range: [0, -1]
+    model:
+      model:
+        path: defog/sqlcoder-7b-2
+  - layer_range: [0, -1]
+    model:
+      model:
+        path: beomi/llama-2-ko-7b
+```

.ipynb_checkpoints/mergekit_config-checkpoint.yml

@@ -0,0 +1,22 @@
+base_model:
+  model:
+    path: defog/sqlcoder-7b-2
+dtype: float16
+merge_method: slerp
+parameters:
+  t:
+  - filter: self_attn
+    value: [0.0, 0.5, 0.3, 0.7, 1.0]
+  - filter: mlp
+    value: [1.0, 0.5, 0.7, 0.3, 0.0]
+  - value: 0.5
+slices:
+- sources:
+  - layer_range: [0, -1]
+    model:
+      model:
+        path: defog/sqlcoder-7b-2
+  - layer_range: [0, -1]
+    model:
+      model:
+        path: beomi/llama-2-ko-7b

.ipynb_checkpoints/model.safetensors.index-checkpoint.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors", "lm_head.weight": "model-00001-of-00001.safetensors"}}

README.md

@@ -0,0 +1,53 @@
+---
+base_model:
+- beomi/llama-2-ko-7b
+- defog/sqlcoder-7b-2
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# sqlcoder-7b-2-slerp
+
+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:
+* [beomi/llama-2-ko-7b](https://huggingface.co/beomi/llama-2-ko-7b)
+* [defog/sqlcoder-7b-2](https://huggingface.co/defog/sqlcoder-7b-2)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model:
+  model:
+    path: defog/sqlcoder-7b-2
+dtype: float16
+merge_method: slerp
+parameters:
+  t:
+  - filter: self_attn
+    value: [0.0, 0.5, 0.3, 0.7, 1.0]
+  - filter: mlp
+    value: [1.0, 0.5, 0.7, 0.3, 0.0]
+  - value: 0.5
+slices:
+- sources:
+  - layer_range: [0, -1]
+    model:
+      model:
+        path: defog/sqlcoder-7b-2
+  - layer_range: [0, -1]
+    model:
+      model:
+        path: beomi/llama-2-ko-7b
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "defog/sqlcoder-7b-2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": -1,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_size": 32016
+}

mergekit_config.yml

@@ -0,0 +1,22 @@
+base_model:
+  model:
+    path: defog/sqlcoder-7b-2
+dtype: float16
+merge_method: slerp
+parameters:
+  t:
+  - filter: self_attn
+    value: [0.0, 0.5, 0.3, 0.7, 1.0]
+  - filter: mlp
+    value: [1.0, 0.5, 0.7, 0.3, 0.0]
+  - value: 0.5
+slices:
+- sources:
+  - layer_range: [0, -1]
+    model:
+      model:
+        path: defog/sqlcoder-7b-2
+  - layer_range: [0, -1]
+    model:
+      model:
+        path: beomi/llama-2-ko-7b

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aba336631cac2bfa799a33a2ffce43ff3c82cb27b831779ea33054ae2130604
+size 524558656

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors", "lm_head.weight": "model-00001-of-00001.safetensors"}}