Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,65 @@
+---
+base_model:
+- Sela223/Repose-Marlin-12B
+- Sela223/Captain-Foxfire-12B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merged
+
+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](https://en.wikipedia.org/wiki/Slerp) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Sela223/Repose-Marlin-12B](https://huggingface.co/Sela223/Repose-Marlin-12B)
+* [Sela223/Captain-Foxfire-12B](https://huggingface.co/Sela223/Captain-Foxfire-12B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: Sela223/Captain-Foxfire-12B
+dtype: bfloat16
+merge_method: slerp
+tokenizer_source: base
+
+slices:
+  - sources:
+      - model: Sela223/Captain-Foxfire-12B
+        layer_range: [0, 40]
+      - model: Sela223/Repose-Marlin-12B
+        layer_range: [0, 40]
+
+parameters:
+  rescale: true
+  t:
+    - filter: ".*(q_proj|k_proj|v_proj).*"
+      value: [0.0, 0.1, 0.25, 0.4, 0.5, 0.5, 0.5, 0.5, 0.4, 0.25, 0.1, 0.0]
+    - filter: ".*o_proj.*"
+      value: [0.0, 0.1, 0.2, 0.35, 0.5, 0.5, 0.5, 0.5, 0.35, 0.2, 0.1, 0.0]
+    - filter: self_attn
+      value: [0.0, 0.1, 0.25, 0.4, 0.5, 0.5, 0.5, 0.5, 0.4, 0.25, 0.1, 0.0]
+
+    - filter: ".*(gate_proj|up_proj|down_proj).*"
+      value: [0.0, 0.15, 0.3, 0.45, 0.5, 0.5, 0.5, 0.5, 0.45, 0.3, 0.15, 0.0]
+    - filter: mlp
+      value: [0.0, 0.15, 0.3, 0.45, 0.5, 0.5, 0.5, 0.5, 0.45, 0.3, 0.15, 0.0]
+
+    - filter: ".*(input_layernorm|post_attention_layernorm|layernorm).*"
+      value: [0.0, 0.3, 0.5, 0.6, 0.4, 0.0, 0.0, 0.4, 0.6, 0.5, 0.3, 0.0]
+    
+    - filter: "^(embed_tokens|lm_head)$"
+      value: 0.5
+
+    - value: [0.0, 0.3, 0.5, 0.6, 0.4, 0.0, 0.0, 0.4, 0.6, 0.5, 0.3, 0.0]
+```

chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,34 @@
+base_model: Sela223/Captain-Foxfire-12B
+dtype: bfloat16
+merge_method: slerp
+tokenizer_source: base
+
+slices:
+  - sources:
+      - model: Sela223/Captain-Foxfire-12B
+        layer_range: [0, 40]
+      - model: Sela223/Repose-Marlin-12B
+        layer_range: [0, 40]
+
+parameters:
+  rescale: true
+  t:
+    - filter: ".*(q_proj|k_proj|v_proj).*"
+      value: [0.0, 0.1, 0.25, 0.4, 0.5, 0.5, 0.5, 0.5, 0.4, 0.25, 0.1, 0.0]
+    - filter: ".*o_proj.*"
+      value: [0.0, 0.1, 0.2, 0.35, 0.5, 0.5, 0.5, 0.5, 0.35, 0.2, 0.1, 0.0]
+    - filter: self_attn
+      value: [0.0, 0.1, 0.25, 0.4, 0.5, 0.5, 0.5, 0.5, 0.4, 0.25, 0.1, 0.0]
+
+    - filter: ".*(gate_proj|up_proj|down_proj).*"
+      value: [0.0, 0.15, 0.3, 0.45, 0.5, 0.5, 0.5, 0.5, 0.45, 0.3, 0.15, 0.0]
+    - filter: mlp
+      value: [0.0, 0.15, 0.3, 0.45, 0.5, 0.5, 0.5, 0.5, 0.45, 0.3, 0.15, 0.0]
+
+    - filter: ".*(input_layernorm|post_attention_layernorm|layernorm).*"
+      value: [0.0, 0.3, 0.5, 0.6, 0.4, 0.0, 0.0, 0.4, 0.6, 0.5, 0.3, 0.0]
+    
+    - filter: "^(embed_tokens|lm_head)$"
+      value: 0.5
+
+    - value: [0.0, 0.3, 0.5, 0.6, 0.4, 0.0, 0.0, 0.4, 0.6, 0.5, 0.3, 0.0]

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2592758f862ee6eedb5f6032e7b51024663f107bd89b7f67f748e1055e8692
+size 4865489336

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2922f48c4d59f185136a0ecb88ffb5cb7eb5d93f10c62953265b207daae79c9d
+size 4907529456

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1db56e01fcd8e3c13e063344a8e2a4d4b330608e5c9f4b49f10ae045a314b85
+size 4907529464

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc0a393e7cac03db37e1f0f994ab6b8a0eafad65204cc5570dbabbb71470848
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceec0bc9c27997d907e02b9cae6a572cd993a0189a830ca26ce4e7c217faef65
+size 4907529392

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_size": 24495564800,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0de30a5895b1aff2e470e085b9898756108ab32944ee156370ad93c2bc373b40
+size 17078343

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {},
+  "pad_token": "<pad>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}