Add files using upload-large-folder tool

config.json

@@ -0,0 +1,26 @@
+{
+  "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": 32768,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.51.3"
+}

mergekit_config.yml

@@ -0,0 +1,23 @@
+# Mistral Model Merge Recipe: Coding + Reasoning
+# This recipe preserves both coding and reasoning capabilities
+
+models:
+  - model: mistralai/Devstral-Small-2505
+    # Replace with your coding model (e.g., "codellama/CodeLlama-7b-Instruct-hf")
+    parameters:
+      density: 0.6
+      weight: 0.55
+  - model: mistralai/Magistral-Small-2506
+    # Replace with your reasoning model (e.g., "mistralai/Mistral-7B-Instruct-v0.2")
+    parameters:
+      density: 0.6
+      weight: 0.45
+
+merge_method: dare_ties
+base_model: mistralai/Devstral-Small-2505  # Base Mistral model
+
+parameters:
+  normalize: true
+  int8_mask: true
+  
+dtype: bfloat16

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae2d4d77f6f40c4c5936d1c322cb573f8a52e201bb0edcd91c1e6f9937027ab
+size 4907389312

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c7c6407c856ea0b68dcce48ae3a68582787c4131d7040cfbe0b220df5efb36e
+size 4781592832

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95f153c0aa4013b5b29555917fc0a4128a8853117ee2a627db8ff6c8f14040e
+size 4781592816

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737d431407af9cbb1f24412c47c19b9e9f07814cb6d91d225c9eb90d89268947
+size 4886471592

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b2924a9279f902ad1eaba1075afb0476f600299e1cab6720bdca0c61aadd13
+size 4781592832

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:850efefa584d07c8022a5e11c708841ed49f23ea9f63271433e430bc9c33f25c
+size 4781592816

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28204ea886a658d61b49d5ad6f36913ea2af246e3bd5bbe8f7b25864c0f1de5f
+size 4886471592

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0521c67a7130a6dd7e0db372bd3e60424ffc6aa86ba9b149d3674b7f676cd320
+size 4781592832

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d091fb00cd95da20f08bd43eb281004dc4048f78c232517819a0862c63779d15
+size 4781592800

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e5a57a790f95fb82c0db7c8a35037904e105598aba6dbd6ece5541c8b4140c
+size 3774959456

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"lm_head.weight": "model-00001-of-00010.safetensors", "model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.norm.weight": "model-00010-of-00010.safetensors"}}

params.json

@@ -0,0 +1,12 @@
+{
+  "dim": 5120,
+  "n_layers": 40,
+  "head_dim": 128,
+  "hidden_dim": 32768,
+  "n_heads": 32,
+  "n_kv_heads": 8,
+  "rope_theta": 1000000000.0,
+  "norm_eps": 1e-05,
+  "vocab_size": 131072
+}
+