Upload folder using huggingface_hub

README.md

@@ -0,0 +1,69 @@
+---
+base_model:
+- rootxhacker/mini-Llama-70M-SFT-math
+- rootxhacker/mini-Llama-70M-SFT
+- rootxhacker/mini-Llama-70M-SFT-ifeval
+- rootxhacker/mini-Llama-70M-SFT-COT
+- rootxhacker/mini-Llama-70M-SFT-medical
+- rootxhacker/mini-Llama-70M-SFT-v2
+- rootxhacker/mini-Llama-70M-SFT-code
+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:
+* [rootxhacker/mini-Llama-70M-SFT-math](https://huggingface.co/rootxhacker/mini-Llama-70M-SFT-math)
+* [rootxhacker/mini-Llama-70M-SFT](https://huggingface.co/rootxhacker/mini-Llama-70M-SFT)
+* [rootxhacker/mini-Llama-70M-SFT-ifeval](https://huggingface.co/rootxhacker/mini-Llama-70M-SFT-ifeval)
+* [rootxhacker/mini-Llama-70M-SFT-COT](https://huggingface.co/rootxhacker/mini-Llama-70M-SFT-COT)
+* [rootxhacker/mini-Llama-70M-SFT-medical](https://huggingface.co/rootxhacker/mini-Llama-70M-SFT-medical)
+* [rootxhacker/mini-Llama-70M-SFT-v2](https://huggingface.co/rootxhacker/mini-Llama-70M-SFT-v2)
+* [rootxhacker/mini-Llama-70M-SFT-code](https://huggingface.co/rootxhacker/mini-Llama-70M-SFT-code)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-v2  # Core reasoning
+        layer_range: [0, 5]  # Full 6 layers
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-COT
+        layer_range: [0, 5]  # Full 6 layers
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-medical
+        layer_range: [0, 5]
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-code
+        layer_range: [0, 5]
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-math
+        layer_range: [0, 5]
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-ifeval
+        layer_range: [0, 4]  # 5 layers
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-v2
+        layer_range: [0, 4]  # 5 layers
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT
+        layer_range: [0, 4]  # 5 layers
+merge_method: passthrough
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 256,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 37,
+  "num_key_value_heads": 6,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,27 @@
+slices:
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-v2  # Core reasoning
+        layer_range: [0, 5]  # Full 6 layers
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-COT
+        layer_range: [0, 5]  # Full 6 layers
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-medical
+        layer_range: [0, 5]
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-code
+        layer_range: [0, 5]
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-math
+        layer_range: [0, 5]
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-ifeval
+        layer_range: [0, 4]  # 5 layers
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT-v2
+        layer_range: [0, 4]  # 5 layers
+  - sources:
+      - model: rootxhacker/mini-Llama-70M-SFT
+        layer_range: [0, 4]  # 5 layers
+merge_method: passthrough
+dtype: bfloat16

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f9beca11a087c7833224ae9776ccee0c0de1c2ca3215bcaf96b1b6dfa6adcf
+size 447632856

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

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