Duplicate from aetherwiing/MN-12B-Starcannon-v3

Co-authored-by: Auri <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,51 @@
+---
+base_model:
+- anthracite-org/magnum-12b-v2
+- nothingiisreal/MN-12B-Celeste-V1.9
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Mistral Nemo 12B Starcannon v3
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). Artbitrary update, because I know that people would request it. Didn't have much time to test it, tbh, but feels nice enough? It's up to y'all to decide if it's an upgrade, sidegrade or downgrade. At least now both models have ChatML trained, there's that.
+<br>
+[Static GGUF (by Mradermacher)](https://huggingface.co/mradermacher/MN-12B-Starcannon-v3-GGUF) <br>
+[Imatrix GGUF (by Mradermacher)](https://huggingface.co/mradermacher/MN-12B-Starcannon-v3-i1-GGUF) <br>
+[EXL2 (by kingbri of RoyalLab)](https://huggingface.co/royallab/MN-12B-Starcannon-v3-exl2)
+## Merge Details
+### Merge Method
+
+This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [nothingiisreal/MN-12B-Celeste-V1.9](https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9) as a base.
+
+### Merge Fodder
+
+The following models were included in the merge:
+* [anthracite-org/magnum-12b-v2](https://huggingface.co/anthracite-org/magnum-12b-v2)
+* [nothingiisreal/MN-12B-Celeste-V1.9](https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+    - model: anthracite-org/magnum-12b-v2
+      parameters:
+        density: 0.3
+        weight: 0.5
+    - model: nothingiisreal/MN-12B-Celeste-V1.9
+      parameters:
+        density: 0.7
+        weight: 0.5
+
+merge_method: ties
+base_model: nothingiisreal/MN-12B-Celeste-V1.9
+parameters:
+    normalize: true
+    int8_mask: true
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "nothingiisreal/MN-12B-Celeste-V1.9",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "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,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": false,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,16 @@
+models:
+    - model: anthracite-org/magnum-12b-v2
+      parameters:
+        density: 0.3
+        weight: 0.5
+    - model: nothingiisreal/MN-12B-Celeste-V1.9
+      parameters:
+        density: 0.7
+        weight: 0.5
+
+merge_method: ties
+base_model: nothingiisreal/MN-12B-Celeste-V1.9
+parameters:
+    normalize: true
+    int8_mask: true
+dtype: bfloat16

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb72c17e4ca589a69889c2cf1149fce1e72de4ef6aa7f3a4cc6e188756ffdfa2
+size 4865489336

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38edf18692a150177a356c9255a26beb7e0f2ccabd931d833110ceaa72caa4b5
+size 4907529456

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d167cc52e534050d4cab7f652b564057b0b6217c643cebcea7ed8f68d6d309
+size 4907529464

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4e01a922b3f4eab6e653061c10d09b3756b7156dd5d6394f2e73f599e185d0
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c2a066b78272b400630e32a0860ab30ab6d86aeeaebd48f558cffd98d78b661
+size 4907529392

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 24495564800}, "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"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}