Upload folder using huggingface_hub

README.md

@@ -0,0 +1,103 @@
+---
+base_model:
+- mistral-community/Codestral-22B-v0.1
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+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 passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [mistral-community/Codestral-22B-v0.1](https://huggingface.co/mistral-community/Codestral-22B-v0.1)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+  slices:
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 0
+          - 8
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 7
+          - 8
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 16
+          - 24
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 23
+          - 24
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 32
+          - 40
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 39
+          - 40
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 48
+          - 56
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 55
+          - 56
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+
+  merge_method: passthrough
+  dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistral-community/Codestral-22B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 36,
+  "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": "4.41.0",
+  "use_cache": true,
+  "vocab_size": 32768
+}

mergekit_config.yml

@@ -0,0 +1,73 @@
+
+  slices:
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 0
+          - 8
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 7
+          - 8
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 16
+          - 24
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 23
+          - 24
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 32
+          - 40
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 39
+          - 40
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 48
+          - 56
+  - sources:
+      - model: mistral-community/Codestral-22B-v0.1
+        layer_range:
+          - 55
+          - 56
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0
+            - filter: down_proj
+              value: 0
+            - value: 1
+
+  merge_method: passthrough
+  dtype: bfloat16

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23282440c70774a5d585d3f9b2de9adf78e9967f7ac4d1ad21f023cd7f358c97
+size 4907476528

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7db4fc90b3024d1e444034ac21f4bf41730439e7fcdfe0dd5338def7e929e73
+size 4932667672

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1eec4fb9e80176d5f6837f13db26d703bf3a590932456a25b45b953047a0d9
+size 4995570416

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8e776463ff254e35d7e6d087a7697a609eec93dbddcef1b06a4f95ed2667e4
+size 4894919160

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c444197b0b07cf4a1b7b83e7c774a8c293c323e6ff9aaf883dae114c84c3568e
+size 4882323736

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb9a980a332116d23368532d5763927661bf2c5758106865a5fac20fdde842c
+size 4278343576

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 28891262976}, "weight_map": {"lm_head.weight": "model-00001-of-00006.safetensors", "model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.safetensors"}}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}