Automated upload of Merge Test 2 (Sibling Violation) via DELLA-Merging

README.md

@@ -0,0 +1,54 @@
+---
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+- nvidia/Nemotron-Research-Reasoning-Qwen-1.5B
+- nvidia/OpenMath-Nemotron-1.5B
+- Fate-Zero/Archer2.0-Code-1.5B-Preview
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge_test_2
+
+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 [DELLA](https://arxiv.org/abs/2406.11617) merge method using [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [nvidia/Nemotron-Research-Reasoning-Qwen-1.5B](https://huggingface.co/nvidia/Nemotron-Research-Reasoning-Qwen-1.5B)
+* [nvidia/OpenMath-Nemotron-1.5B](https://huggingface.co/nvidia/OpenMath-Nemotron-1.5B)
+* [Fate-Zero/Archer2.0-Code-1.5B-Preview](https://huggingface.co/Fate-Zero/Archer2.0-Code-1.5B-Preview)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+merge_method: della
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+dtype: bfloat16
+models:
+  - model: nvidia/OpenMath-Nemotron-1.5B
+    parameters:
+      weight: 1.0
+      density: 0.6
+      epsilon: 0.3
+  - model: nvidia/Nemotron-Research-Reasoning-Qwen-1.5B
+    parameters:
+      weight: 1.0
+      density: 0.6
+      epsilon: 0.3
+  - model: Fate-Zero/Archer2.0-Code-1.5B-Preview
+    parameters:
+      weight: 1.0
+      density: 0.6
+      epsilon: 0.3
+
+```

config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.10.2",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "eos_token_id": 151643,
+  "do_sample": true,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.39.3"
+}

mergekit_config.yml

@@ -0,0 +1,19 @@
+merge_method: della
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+dtype: bfloat16
+models:
+  - model: nvidia/OpenMath-Nemotron-1.5B
+    parameters:
+      weight: 1.0
+      density: 0.6
+      epsilon: 0.3
+  - model: nvidia/Nemotron-Research-Reasoning-Qwen-1.5B
+    parameters:
+      weight: 1.0
+      density: 0.6
+      epsilon: 0.3
+  - model: Fate-Zero/Archer2.0-Code-1.5B-Preview
+    parameters:
+      weight: 1.0
+      density: 0.6
+      epsilon: 0.3

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9fb9a3ab2bfd1a0c9937ff93607b0093655f40951eb899cff9270b161bad22
+size 3554214752

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sp_model_kwargs": {},
+  "unk_token": null,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}"
+}