初始化项目，由ModelHub XC社区提供模型

Model: Minami-su/Qwen1.5-0.5B-Chat_mistral
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 +1,85 @@
+---
+license: other
+license_name: qwen
+license_link: >-
+  https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
+language:
+- en
+- zh
+library_name: transformers
+pipeline_tag: text-generation
+inference: false
+tags:
+- mistral
+- qwen
+- qwen1.5
+- qwen2
+---
+This is the Mistral version of [Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) model by Alibaba Cloud.
+The original codebase can be found at: (https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/llamafy_qwen.py).
+I have made modifications to make it compatible with qwen1.5.
+This model is converted with https://github.com/Minami-su/character_AI_open/blob/main/mistral_qwen2.py
+
+## special
+
+1.Before using this model, you need to modify modeling_mistral.py in transformers library
+
+2.vim /root/anaconda3/envs/train/lib/python3.9/site-packages/transformers/models/mistral/modeling_mistral.py
+
+3.find MistralAttention,
+
+4.modify q,k,v,o bias=False ----->, bias=config.attention_bias
+
+Before:
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62d7f90b102d144db4b4245b/AKj_fwEoLUKWZ4mViYW-q.png)
+After:
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62d7f90b102d144db4b4245b/A2gSwq9l6Zx8X1qegtgvE.png)
+
+
+## Differences between qwen2 mistral and qwen2 llamafy
+
+Compared to qwen2 llamafy,qwen2 mistral can use sliding window attention,qwen2 mistral is faster than qwen2 llamafy, and the context length is better
+
+
+Usage:
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+tokenizer = AutoTokenizer.from_pretrained("Minami-su/Qwen1.5-0.5B-Chat_mistral")
+model = AutoModelForCausalLM.from_pretrained("Minami-su/Qwen1.5-0.5B-Chat_mistral", torch_dtype="auto", device_map="auto")
+streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+
+messages = [
+    {"role": "user", "content": "Who are you?"}
+]
+inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+inputs = inputs.to("cuda")
+generate_ids = model.generate(inputs,max_length=2048, streamer=streamer)
+
+```
+
+## Test
+load in 4bit
+```
+hf-causal (pretrained=Qwen1.5-0.5B-Chat), limit: None, provide_description: False, num_fewshot: 0, batch_size: 32
+|    Task     |Version| Metric |Value |   |Stderr|
+|-------------|------:|--------|-----:|---|-----:|
+|arc_challenge|      0|acc     |0.2389|±  |0.0125|
+|             |       |acc_norm|0.2688|±  |0.0130|
+|truthfulqa_mc|      1|mc1     |0.2534|±  |0.0152|
+|             |       |mc2     |0.4322|±  |0.0151|
+|winogrande   |      0|acc     |0.5564|±  |0.0140|
+```
+load in 4bit
+```
+hf-causal (pretrained=Qwen1.5-0.5B-Chat_mistral), limit: None, provide_description: False, num_fewshot: 0, batch_size: 32
+|    Task     |Version| Metric |Value |   |Stderr|
+|-------------|------:|--------|-----:|---|-----:|
+|arc_challenge|      0|acc     |0.2398|±  |0.0125|
+|             |       |acc_norm|0.2705|±  |0.0130|
+|truthfulqa_mc|      1|mc1     |0.2534|±  |0.0152|
+|             |       |mc2     |0.4322|±  |0.0151|
+|winogrande   |      0|acc     |0.5549|±  |0.0140|
+```
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "mistral",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": true,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.1,
+  "top_p": 0.8,
+  "transformers_version": "4.37.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52cc9f56b4902c086f5702c2d9c247dc76fe08c9ee51df0b09dada7ed66344f
+size 1239290870

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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 %}{{'<|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
+}