Upload folder using huggingface_hub

README.md

@@ -0,0 +1,39 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- mistralai/Mistral-Nemo-Instruct-2407
+- mistralai/Mistral-Nemo-Base-2407
+---
+
+# Mistral-Nemo-Instruct-2407-Mistral-Nemo-Base-2407-linear-merge
+
+Mistral-Nemo-Instruct-2407-Mistral-Nemo-Base-2407-linear-merge is a sophisticated language model resulting from the strategic merging of two distinct models: [Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) and [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407). This merging process was executed using [mergekit](https://github.com/cg123/mergekit), a specialized tool designed for precise model blending, ensuring optimal performance and synergy between the merged architectures.
+
+## 🧩 Merge Configuration
+
+The models were merged using a linear interpolation method, which allows for a balanced integration of the two models' capabilities. The configuration details are as follows:
+
+```yaml
+models:
+  - model: mistralai/Mistral-Nemo-Instruct-2407
+    parameters:
+      weight: 0.6
+  - model: mistralai/Mistral-Nemo-Base-2407
+    parameters:
+      weight: 0.4
+merge_method: linear
+parameters:
+  normalize: true
+dtype: float16
+```
+
+## Model Features
+
+This merged model combines the instructive capabilities of Mistral-Nemo-Instruct-2407 with the foundational strengths of Mistral-Nemo-Base-2407. The result is a versatile model that excels in various text generation tasks, offering enhanced context understanding and nuanced text generation. By leveraging the strengths of both parent models, this linear merge provides improved performance across diverse NLP applications.
+
+## Limitations
+
+While the Mistral-Nemo-Instruct-2407-Mistral-Nemo-Base-2407-linear-merge inherits many strengths from its parent models, it may also carry over certain limitations or biases present in those models. Users should be aware of potential biases in generated outputs and the need for careful evaluation in sensitive applications.

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "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": "float16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 131072
+}

linear_config.yaml

@@ -0,0 +1,11 @@
+models:
+  - model: mistralai/Mistral-Nemo-Instruct-2407
+    parameters:
+      weight: 0.6
+  - model: mistralai/Mistral-Nemo-Base-2407
+    parameters:
+      weight: 0.4
+merge_method: linear
+parameters:
+  normalize: true
+dtype: float16

mergekit_config.yml

@@ -0,0 +1,11 @@
+models:
+  - model: mistralai/Mistral-Nemo-Instruct-2407
+    parameters:
+      weight: 0.6
+  - model: mistralai/Mistral-Nemo-Base-2407
+    parameters:
+      weight: 0.4
+merge_method: linear
+parameters:
+  normalize: true
+dtype: float16

model-00001-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fed3740673eb062d7016fe842fa7742634756a7a739c36188f7a311870bf7d1
+size 1342177408

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa77af14cbbc5844ed6ff6207ed0db9d6b58c5a45fa60234d5350cdc77ad947
+size 1342177416

model-00003-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19a8209296ac8d22b627c53d84deefeb516e135a7d822d7a8d0611e2cd57e99
+size 996189872

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5efc29bbc481c29a71a880eddc3b6361f7bd845f2a50ba931ae7bb85133c52
+size 933265088

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f68eae6613fe9eb3881528b5e2abe572855eb1ef759328d8d576314b7d23102
+size 943761328

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b73f1c90bb2338d5c6c4f5b020f637eb105609d37606eb9b6e9b506a0700389
+size 943761328

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098e7a8083eca19857eab87cf1c83b3f05a96782a39f3416ddc0b57d2294b895
+size 996179552

model-00008-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8356144e092b80f94b6927d6a6b58c1f22f55fdcf96c96c6481c27b014d9c7
+size 933265088

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd784823403d10da609ba90d4b7be6e90b416f1b7c465bfcf01c656e2dd2b603
+size 943761328

model-00010-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaec25a23dfdd6880dadc96ce509ded7101011d074012f070c1259f7787a38ae
+size 943761320

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7be1ad0e88b1c935bdf2a0ea5910e4062b638499330a017d74315cdd3ce3dee2
+size 996179552

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1c9262d551d687b341a8e614c627c11050a63fc6b787923afbd21731f4b773
+size 933265088

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb62d7f3b073f4869643896144e30f6fdbc6803d1c3abd05fb4eeb00fdaf992
+size 943761328

model-00014-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:034a421c26b5b61f38a4e9c1a5b906f334fabe8172eeb1490e64a74767304f7f
+size 943761328

model-00015-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5dda50de2ba64976a543f360e7115a1b78da1a76513bde7f5921beb12c6ba90
+size 996179552

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e79312923911bb3817555f61ae1a7119273fb85346357367b6f334b55d5ec4
+size 933265080

model-00017-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f824218d2dbd6fcd83a484791e54a22b329bf08cc5600c18be169da974332d
+size 943761328

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4054955e9e2ad01bcae321647820a78c8d0b9e294242d05f375832e78f26c57
+size 943761328

model-00019-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c345cb2bb1b6dc3d05d43347a9da56aef22b14782dc566243219339c3b5a48f
+size 996179552

model-00020-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20978fa598432334169cb39b127a1665d7a6193a07f59ffcb3cac97f3ad6ae0
+size 933265088

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c0703c4005448ffe7c2391bfdcb84b76efa2495418bfc4603bcb98d4449ca5
+size 943761328

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb5164172446d02d97538875e75fe5e757a7e95d322732b9799a30c1c3dc7374
+size 943761320

model-00023-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e520f3721f673e236ca316230c6f1fb0c34246889d2206ea5f0a785b1d2914
+size 996179536

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb353610b17c836165ef41e2335b39eee932da2f062de70094004638d49c97ff
+size 933265080

model-00025-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72268ad38a637b5ab6342982846d624c95fbc85c99720f266bfe6938e2eb9330
+size 796960544

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-00025.safetensors", "model.embed_tokens.weight": "model-00002-of-00025.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00025.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.21.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.24.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00025.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00013-of-00025.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.26.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.28.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.30.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.32.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00017-of-00025.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.34.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.input_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.37.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00020-of-00025.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.39.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.5.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.input_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00025-of-00025.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00025-of-00025.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00025-of-00025.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.input_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00025-of-00025.safetensors", "model.norm.weight": "model-00025-of-00025.safetensors"}}

special_tokens_map.json

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