Upload folder using huggingface_hub

README.md

@@ -0,0 +1,77 @@
+---
+base_model:
+- Qwen/Qwen2.5-Coder-1.5B-Instruct
+- Qwen/Qwen2.5-Math-1.5B-Instruct
+- Qwen/Qwen2.5-1.5B
+- agentica-org/DeepScaleR-1.5B-Preview
+tags:
+- merge
+- mergekit
+- lazymergekit
+- Qwen/Qwen2.5-Coder-1.5B-Instruct
+- Qwen/Qwen2.5-Math-1.5B-Instruct
+- Qwen/Qwen2.5-1.5B
+- agentica-org/DeepScaleR-1.5B-Preview
+---
+
+# DeepQwenScalerPlus
+
+DeepQwenScalerPlus is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct)
+* [Qwen/Qwen2.5-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct)
+* [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B)
+* [agentica-org/DeepScaleR-1.5B-Preview](https://huggingface.co/agentica-org/DeepScaleR-1.5B-Preview)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+    # no parameters necessary for base model
+  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+    parameters:
+      density: 0.5
+      weight: 0.5
+  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
+    parameters:
+      density: 0.6
+      weight: 0.5
+  - model: Qwen/Qwen2.5-1.5B
+    parameters:
+      density: 0.6
+      weight: 0.5
+  - model: agentica-org/DeepScaleR-1.5B-Preview
+    parameters:
+      density: 0.4
+      weight: 0.6
+merge_method: ties
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+parameters:
+  normalize: true
+dtype: float16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "K00B404/DeepQwenScalerPlus"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "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": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.50.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

mergekit_config.yml

@@ -0,0 +1,25 @@
+
+models:
+  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+    # no parameters necessary for base model
+  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+    parameters:
+      density: 0.5
+      weight: 0.5
+  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
+    parameters:
+      density: 0.6
+      weight: 0.5
+  - model: Qwen/Qwen2.5-1.5B
+    parameters:
+      density: 0.6
+      weight: 0.5
+  - model: agentica-org/DeepScaleR-1.5B-Preview
+    parameters:
+      density: 0.4
+      weight: 0.6
+merge_method: ties
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+parameters:
+  normalize: true
+dtype: float16

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95621081a5c09c5c979ed38a60c9404bd4fbb102bd80c5aae1051ace63a0ee38
+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 %}"
+}