Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,41 @@
+---
+base_model:
+- Alelcv27/Llama3.1-8B-Math-v2
+- Alelcv27/Llama3.1-8B-Code-v2
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Llama3.1-8B-Arcee-Math-Code-v2
+
+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 [Arcee Fusion](https://arcee.ai) merge method using [Alelcv27/Llama3.1-8B-Math-v2](https://huggingface.co/Alelcv27/Llama3.1-8B-Math-v2) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Alelcv27/Llama3.1-8B-Code-v2](https://huggingface.co/Alelcv27/Llama3.1-8B-Code-v2)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: Alelcv27/Llama3.1-8B-Math-v2
+dtype: bfloat16
+merge_method: arcee_fusion
+modules:
+  default:
+    slices:
+    - sources:
+      - layer_range: [0, 32]
+        model: Alelcv27/Llama3.1-8B-Math-v2
+      - layer_range: [0, 32]
+        model: Alelcv27/Llama3.1-8B-Code-v2
+```

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "unsloth_fixed": true,
+  "unsloth_version": "2026.3.5",
+  "use_cache": false,
+  "vocab_size": 128256
+}

mergekit_config.yml

@@ -0,0 +1,11 @@
+base_model: Alelcv27/Llama3.1-8B-Math-v2
+dtype: bfloat16
+merge_method: arcee_fusion
+modules:
+  default:
+    slices:
+    - sources:
+      - layer_range: [0, 32]
+        model: Alelcv27/Llama3.1-8B-Math-v2
+      - layer_range: [0, 32]
+        model: Alelcv27/Llama3.1-8B-Code-v2

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd1974ca99ed148b888af5afde32a328f6f892b02489c7a512e173551ec504b
+size 4991255560

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0fa7b34b2ed3b87de51febfec08644cdbd41df39cfd23e96bf196339c5c83df
+size 4915910288

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb8e59de0ae97352c8c0f9f4d1dbd4d280e167a98390005649c97887be794e15
+size 4999813128

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b4df4f52a20d7adee198c056c0b56ce912dfb17aeb8a1ee246ad0588f88b8a
+size 4999813120

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e211c8e63e23a72bc431fe29ea94042efd0bf4f7622c5e4b769c53e27680d102
+size 4832007504

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc86bba2f732606ed4868b30a997031cc490416927509bad06f57f5336fe4b13
+size 4999813096

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a64f28bbc9579a0c355aa56148f2518cda55416589d34002ef71f17440fb30c
+size 2382465960

model.safetensors.index.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "from_slow": true,
+  "is_local": false,
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n"
+}