初始化项目，由ModelHub XC社区提供模型

Model: QwenCollection/CleverQwen2-1.5B
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,58 @@
+---
+base_model:
+- cognitivecomputations/dolphin-2.9.3-qwen2-1.5b
+- trollek/Qwen2-1.5B-Instruct-Abliterated
+- M4-ai/Hercules-5.0-Qwen2-1.5B
+- Replete-AI/Replete-Coder-Qwen2-1.5b
+library_name: transformers
+tags:
+- mergekit
+- merge
+license: apache-2.0
+language:
+- en
+---
+# CleverQwen2-1.5B
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+It has grown by about 300M parameters and I don't know why. I would like to know though. It works as expexted - **amazing** - I just can't see any reason for the Qwen2 models to gain parameters when merged.
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [trollek/Qwen2-1.5B-Instruct-Abliterated](https://huggingface.co/trollek/Qwen2-1.5B-Instruct-Abliterated) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [cognitivecomputations/dolphin-2.9.3-qwen2-1.5b](https://huggingface.co/cognitivecomputations/dolphin-2.9.3-qwen2-1.5b)
+* [M4-ai/Hercules-5.0-Qwen2-1.5B](https://huggingface.co/M4-ai/Hercules-5.0-Qwen2-1.5B)
+* [Replete-AI/Replete-Coder-Qwen2-1.5b](https://huggingface.co/Replete-AI/Replete-Coder-Qwen2-1.5b)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: Replete-AI/Replete-Coder-Qwen2-1.5b
+  - model: M4-ai/Hercules-5.0-Qwen2-1.5B
+  - model: cognitivecomputations/dolphin-2.9.3-qwen2-1.5b
+merge_method: model_stock
+base_model: trollek/Qwen2-1.5B-Instruct-Abliterated
+architecture: qwen2
+dtype: bfloat16
+```
+
+## Quants
+
+- [trollek/CleverQwen2-1.5B-GGUF](https://huggingface.co/trollek/CleverQwen2-1.5B-GGUF)
+
+### Ollama
+
+```bash
+ollama pull trollek/cleverqwen2:1.5b-q4_k_s
+ollama pull trollek/cleverqwen2:1.5b-q5_k_s
+ollama pull trollek/cleverqwen2:1.5b-q6_k
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "trollek/CleverQwen2-1.5B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

mergekit_config.yml

@@ -0,0 +1,8 @@
+models:
+  - model: Replete-AI/Replete-Coder-Qwen2-1.5b
+  - model: M4-ai/Hercules-5.0-Qwen2-1.5B
+  - model: cognitivecomputations/dolphin-2.9.3-qwen2-1.5b
+merge_method: model_stock
+base_model: trollek/Qwen2-1.5B-Instruct-Abliterated
+architecture: qwen2
+dtype: bfloat16

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9b4607ca2a8af2155a7925b571c64d8c2e77da55743ae4b7542ee617fd8afd
+size 3554214752

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}