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
+Mini-Tcomanr-R1-1.8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Mini-Tcomanr-R1-1.8B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f774d93efa3c916c0b89e013b346902eb2264588d288d56fb65a8f5d9e2696c9
+size 1894533984

README.md

@@ -1,3 +1,75 @@
 ---
-license: apache-2.0
+base_model:
+- agentica-org/DeepScaleR-1.5B-Preview
+- agentica-org/DeepCoder-1.5B-Preview
+- Josephgflowers/DeepSeek-R1-Distill-Qwen-1.5B-LIMO
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+- huihui-ai/DeepSeek-R1-Distill-Qwen-1.5B-abliterated
+- ibndias/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
+- ertghiu256/Deepseek-R1-Distill-1.5B-code-instruct
+- prithivMLmods/QwQ-R1-Distill-1.5B-CoT
+library_name: transformers
+tags:
+- mergekit
+- merge
+
 ---
+# Mini-Tcomanr-R1
+
+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 [TIES](https://arxiv.org/abs/2306.01708) 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:
+* [agentica-org/DeepScaleR-1.5B-Preview](https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview)
+* [agentica-org/DeepCoder-1.5B-Preview](https://huggingface.co/agentica-org/DeepCoder-1.5B-Preview)
+* [Josephgflowers/DeepSeek-R1-Distill-Qwen-1.5B-LIMO](https://huggingface.co/Josephgflowers/DeepSeek-R1-Distill-Qwen-1.5B-LIMO)
+* [huihui-ai/DeepSeek-R1-Distill-Qwen-1.5B-abliterated](https://huggingface.co/huihui-ai/DeepSeek-R1-Distill-Qwen-1.5B-abliterated)
+* [ibndias/DeepSeek-R1-Distill-Qwen-1.5B-GRPO](https://huggingface.co/ibndias/DeepSeek-R1-Distill-Qwen-1.5B-GRPO)
+* [ertghiu256/Deepseek-R1-Distill-1.5B-code-instruct](https://huggingface.co/ertghiu256/Deepseek-R1-Distill-1.5B-code-instruct)
+* [prithivMLmods/QwQ-R1-Distill-1.5B-CoT](https://huggingface.co/prithivMLmods/QwQ-R1-Distill-1.5B-CoT)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: prithivMLmods/QwQ-R1-Distill-1.5B-CoT
+    parameters:
+      weight: 0.5
+  - model: ertghiu256/Deepseek-R1-Distill-1.5B-code-instruct
+    parameters:
+      weight: 1.0
+  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-1.5B-abliterated
+    parameters:
+      weight: 0.85
+  - model: Josephgflowers/DeepSeek-R1-Distill-Qwen-1.5B-LIMO
+    parameters:
+      weight: 0.5
+  - model: ibndias/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
+    parameters:
+      weight: 0.3
+  - model: agentica-org/DeepScaleR-1.5B-Preview
+    parameters:
+      weight: 0.95
+  - model: agentica-org/DeepCoder-1.5B-Preview
+    parameters:
+      weight: 1.0
+  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+    parameters:
+      weight: 1.0
+merge_method: ties
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+parameters:
+  normalize: true
+  int8_mask: true
+  lambda: 1.0
+  rescale: true
+dtype: float16
+```

config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float16",
+  "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,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

mergekit_config.yml

@@ -0,0 +1,33 @@
+models:
+  - model: prithivMLmods/QwQ-R1-Distill-1.5B-CoT
+    parameters:
+      weight: 0.5
+  - model: ertghiu256/Deepseek-R1-Distill-1.5B-code-instruct
+    parameters:
+      weight: 1.0
+  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-1.5B-abliterated
+    parameters:
+      weight: 0.85
+  - model: Josephgflowers/DeepSeek-R1-Distill-Qwen-1.5B-LIMO
+    parameters:
+      weight: 0.5
+  - model: ibndias/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
+    parameters:
+      weight: 0.3
+  - model: agentica-org/DeepScaleR-1.5B-Preview
+    parameters:
+      weight: 0.95
+  - model: agentica-org/DeepCoder-1.5B-Preview
+    parameters:
+      weight: 1.0
+  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+    parameters:
+      weight: 1.0
+merge_method: ties
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+parameters:
+  normalize: true
+  int8_mask: true
+  lambda: 1.0
+  rescale: true
+dtype: float16

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b8fc1637d6dc532f3a5d483c000a11d257e5f6f191c3c0b78017385b7a0c82
+size 3554214416

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 %}"
+}