Upload 18 files

README.md

@@ -0,0 +1,95 @@
+---
+base_model:
+- TheDrummer/Rocinante-12B-v1
+- jtatman/mistral_nemo_12b_reasoning_psychology_lora
+- Epiculous/Azure_Dusk-v0.2
+- nbeerbower/mistral-nemo-bophades-12B
+- Epiculous/Crimson_Dawn-v0.2
+- nbeerbower/mistral-nemo-wissenschaft-12B
+- anthracite-org/magnum-v2-12b
+- TheDrummer/Rocinante-12B-v1.1
+- anthracite-org/magnum-v2.5-12b-kto
+- mpasila/Mistral-freeLiPPA-LoRA-12B
+- anthracite-org/magnum-v2.5-12b-kto
+- jeiku/Aura-NeMo-12B
+- nbeerbower/mistral-nemo-cc-12B
+- UsernameJustAnother/Nemo-12B-Marlin-v8
+- elinas/Chronos-Gold-12B-1.0
+- SillyTilly/mistralai_Mistral-Nemo-Base-2407
+- nbeerbower/Lyra4-Gutenberg-12B
+- nbeerbower/mistral-nemo-gutenberg-12B-v4
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# 6hsWEeh
+
+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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [SillyTilly/mistralai_Mistral-Nemo-Base-2407](https://huggingface.co/SillyTilly/mistralai_Mistral-Nemo-Base-2407) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [TheDrummer/Rocinante-12B-v1](https://huggingface.co/TheDrummer/Rocinante-12B-v1) + [jtatman/mistral_nemo_12b_reasoning_psychology_lora](https://huggingface.co/jtatman/mistral_nemo_12b_reasoning_psychology_lora)
+* [Epiculous/Azure_Dusk-v0.2](https://huggingface.co/Epiculous/Azure_Dusk-v0.2)
+* [nbeerbower/mistral-nemo-bophades-12B](https://huggingface.co/nbeerbower/mistral-nemo-bophades-12B)
+* [Epiculous/Crimson_Dawn-v0.2](https://huggingface.co/Epiculous/Crimson_Dawn-v0.2)
+* [nbeerbower/mistral-nemo-wissenschaft-12B](https://huggingface.co/nbeerbower/mistral-nemo-wissenschaft-12B)
+* [anthracite-org/magnum-v2-12b](https://huggingface.co/anthracite-org/magnum-v2-12b)
+* [TheDrummer/Rocinante-12B-v1.1](https://huggingface.co/TheDrummer/Rocinante-12B-v1.1)
+* [anthracite-org/magnum-v2.5-12b-kto](https://huggingface.co/anthracite-org/magnum-v2.5-12b-kto) + [mpasila/Mistral-freeLiPPA-LoRA-12B](https://huggingface.co/mpasila/Mistral-freeLiPPA-LoRA-12B)
+* [anthracite-org/magnum-v2.5-12b-kto](https://huggingface.co/anthracite-org/magnum-v2.5-12b-kto) + [jeiku/Aura-NeMo-12B](https://huggingface.co/jeiku/Aura-NeMo-12B)
+* [nbeerbower/mistral-nemo-cc-12B](https://huggingface.co/nbeerbower/mistral-nemo-cc-12B)
+* [UsernameJustAnother/Nemo-12B-Marlin-v8](https://huggingface.co/UsernameJustAnother/Nemo-12B-Marlin-v8)
+* [elinas/Chronos-Gold-12B-1.0](https://huggingface.co/elinas/Chronos-Gold-12B-1.0)
+* [nbeerbower/Lyra4-Gutenberg-12B](https://huggingface.co/nbeerbower/Lyra4-Gutenberg-12B)
+* [nbeerbower/mistral-nemo-gutenberg-12B-v4](https://huggingface.co/nbeerbower/mistral-nemo-gutenberg-12B-v4)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: SillyTilly/mistralai_Mistral-Nemo-Base-2407
+dtype: float32
+merge_method: model_stock
+slices:
+- sources:
+  - layer_range: [0, 40]
+    model: nbeerbower/Lyra4-Gutenberg-12B
+  - layer_range: [0, 40]
+    model: nbeerbower/mistral-nemo-gutenberg-12B-v4
+  - layer_range: [0, 40]
+    model: elinas/Chronos-Gold-12B-1.0
+  - layer_range: [0, 40]
+    model: UsernameJustAnother/Nemo-12B-Marlin-v8
+  - layer_range: [0, 40]
+    model: TheDrummer/Rocinante-12B-v1.1
+  - layer_range: [0, 40]
+    model: Epiculous/Azure_Dusk-v0.2
+  - layer_range: [0, 40]
+    model: Epiculous/Crimson_Dawn-v0.2
+  - layer_range: [0, 40]
+    model: TheDrummer/Rocinante-12B-v1+jtatman/mistral_nemo_12b_reasoning_psychology_lora
+  - layer_range: [0, 40]
+    model: nbeerbower/mistral-nemo-wissenschaft-12B
+  - layer_range: [0, 40]
+    model: nbeerbower/mistral-nemo-bophades-12B
+  - layer_range: [0, 40]
+    model: anthracite-org/magnum-v2.5-12b-kto+mpasila/Mistral-freeLiPPA-LoRA-12B
+  - layer_range: [0, 40]
+    model: nbeerbower/mistral-nemo-cc-12B
+  - layer_range: [0, 40]
+    model: anthracite-org/magnum-v2-12b
+  - layer_range: [0, 40]
+    model: anthracite-org/magnum-v2.5-12b-kto+jeiku/Aura-NeMo-12B
+  - layer_range: [0, 40]
+    model: SillyTilly/mistralai_Mistral-Nemo-Base-2407
+tokenizer_source: unsloth/Mistral-Nemo-Base-2407
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "SillyTilly/mistralai_Mistral-Nemo-Base-2407",
+  "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": "float32",
+  "transformers_version": "4.43.3",
+  "use_cache": true,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,36 @@
+base_model: SillyTilly/mistralai_Mistral-Nemo-Base-2407
+dtype: float32
+merge_method: model_stock
+slices:
+- sources:
+  - layer_range: [0, 40]
+    model: nbeerbower/Lyra4-Gutenberg-12B
+  - layer_range: [0, 40]
+    model: nbeerbower/mistral-nemo-gutenberg-12B-v4
+  - layer_range: [0, 40]
+    model: elinas/Chronos-Gold-12B-1.0
+  - layer_range: [0, 40]
+    model: UsernameJustAnother/Nemo-12B-Marlin-v8
+  - layer_range: [0, 40]
+    model: TheDrummer/Rocinante-12B-v1.1
+  - layer_range: [0, 40]
+    model: Epiculous/Azure_Dusk-v0.2
+  - layer_range: [0, 40]
+    model: Epiculous/Crimson_Dawn-v0.2
+  - layer_range: [0, 40]
+    model: TheDrummer/Rocinante-12B-v1+jtatman/mistral_nemo_12b_reasoning_psychology_lora
+  - layer_range: [0, 40]
+    model: nbeerbower/mistral-nemo-wissenschaft-12B
+  - layer_range: [0, 40]
+    model: nbeerbower/mistral-nemo-bophades-12B
+  - layer_range: [0, 40]
+    model: anthracite-org/magnum-v2.5-12b-kto+mpasila/Mistral-freeLiPPA-LoRA-12B
+  - layer_range: [0, 40]
+    model: nbeerbower/mistral-nemo-cc-12B
+  - layer_range: [0, 40]
+    model: anthracite-org/magnum-v2-12b
+  - layer_range: [0, 40]
+    model: anthracite-org/magnum-v2.5-12b-kto+jeiku/Aura-NeMo-12B
+  - layer_range: [0, 40]
+    model: SillyTilly/mistralai_Mistral-Nemo-Base-2407
+tokenizer_source: unsloth/Mistral-Nemo-Base-2407

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc5ba2bd333cdc297abc9b312e650108cb9264dedd4c16a896942efb39cc8973
+size 2684354688

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55cc4f09366a4f31328cec19a4a7999d6d81d5a1d14b6b2b24d62152c2eefb76
+size 4865497360

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0edb1c0ccd46d0231b4700203ed8a25ae267478545db9fdaa2208ed444c006c6
+size 4949446984

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7688d77592b7777e756c1650faf2efbf3db83a3d38828eefda07ec77775b4044
+size 4865602440

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f8fdc9f3a5670ec888a40ebdbea0d25ebe7e97b8e33b83a4e15f16687c55ef
+size 4949446968

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab892e0cd2e7b0225a6295114e7ff866bf72e268da238c80353170335febeb0d
+size 4865602440

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:263a635c8699a70e3347163e55937896b7237111ec3490f984cc3584e412c62b
+size 4949446968

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6566d5b382c2ed3aa4b6c7a63f6aae74749f0d5a8def118972cee43048fa5af5
+size 4865602440

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce500a38f9904ec51a590484c4061a3d1dcb6e44dff9c7743571f0b69d2f735
+size 4949446984

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eafb15cb0f1e894ac1beecd8c8275dfe6042c406e4ca2ea56d409b077869c8cd
+size 4865602400

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f0c68e365b6ff70ed830b7d5872a839a200aa297514771e698774ef7f64986
+size 2181122072

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 48991129600}, "weight_map": {"lm_head.weight": "model-00001-of-00011.safetensors", "model.embed_tokens.weight": "model-00002-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.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
+  }
+}