Upload folder using huggingface_hub

README.md

@@ -0,0 +1,189 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+- Equall/Saul-Instruct-v1
+---
+
+# Saul-Instruct-Extended
+
+Saul-Instruct-Extended is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+* [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1)
+
+## 🧩 Configuration
+
+```yaml
+  slices:
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 0
+          - 4
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 3
+          - 4
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 4
+          - 8
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 7
+          - 8
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 8
+          - 12
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 11
+          - 12
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 12
+          - 16
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 15
+          - 16
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 16
+          - 20
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 19
+          - 20
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 20
+          - 24
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 23
+          - 24
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 24
+          - 28
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 27
+          - 28
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 28
+          - 32
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 31
+          - 32
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  merge_method: passthrough
+  dtype: bfloat16
+
+
+
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "Equall/Saul-Instruct-v1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,143 @@
+
+  slices:
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 0
+          - 4
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 3
+          - 4
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 4
+          - 8
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 7
+          - 8
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 8
+          - 12
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 11
+          - 12
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 12
+          - 16
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 15
+          - 16
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 16
+          - 20
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 19
+          - 20
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 20
+          - 24
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 23
+          - 24
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 24
+          - 28
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 27
+          - 28
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 28
+          - 32
+  - sources:
+      - model: Equall/Saul-Instruct-v1
+        layer_range:
+          - 31
+          - 32
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  merge_method: passthrough
+  dtype: bfloat16
+
+
+

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:324672dfbf8ec4ec100b61c4a689d4b21ada6b77d91f0ec7ee945861bc181b3c
+size 1912672792

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c041bdff0c0bed04661a15761c493e2550f9b6f50691160ad29b9cf1227210
+size 1889587048

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcaa6bd80ef002a6339ca368478f69f062d6ddda11305f4ee6e194e11935b80f
+size 1979789736

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bbb20193017452ef8e4704c654157c730ab5a459ba3e79bf5bbedf4d7f52927
+size 1979790224

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6897fc8e826fbef2f27e736da319fdbf33afd588683791009cdb21390b47e0f5
+size 1946243984

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870df7b8410391e50c0f64109c08e178da44bf3d3312db78196775ee54b86e85
+size 1979781464

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe873a8d686245a040bfb36bb09c7380f45af6b110e61e66175f5c5b268d0e4
+size 1946227360

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d3f34d80a670466eeae428ccc1a4ba59bf12a024126c9b620ad88eecccef9a2
+size 1923166040

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82c0918896194baba5973b81027520aa36a22d20dd9bd279623ada7c5578d294
+size 1979781464

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb3eef047c030f5e5bd50082b4b1651ac7eddb76f467b5a59ed015b03f3d471
+size 436258288

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.embed_tokens.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00010.safetensors", "lm_head.weight": "model-00008-of-00010.safetensors", "model.norm.weight": "model-00008-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00010-of-00010.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}