Upload 15 files

README.md

@@ -0,0 +1,73 @@
+---
+license: other
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+---
+# Turbcat 72b
+![image/png](3.png)
+![image/png](4.png)
+![image/png](5.png)
+![image/png](6.png)
+![image/png](7.png)
+![image/png](8.png)
+# Release notes
+This is a direct upgrade over cat 70B, with 2x the dataset size(2GB-> 5GB), added Chinese support with quality on par with the original English dataset. 
+The medical COT portion of the dataset has been sponsored by steelskull, and the action packed character play portion was donated by Gryphe's(aesir dataset). Note that 8b is based on llama3 with limited Chinese support due to base model choice. The chat format in 8b is llama3. The 72b has more comprehensive Chinese support and the format will be chatml.
+
+# Data Generation
+In addition to the specified fortifications above, the data generation process is largely the same. Except for added Chinese Ph. D. Entrance exam, Traditional Chinese and Chinese story telling data.
+
+## Special Highlights
+* 20 postdocs (10 Chinese, 10 English speaking doctors specialized in computational biology, biomed, biophysics and biochemistry)participated in the annotation process.
+* GRE and MCAT/Kaoyan questions were manually answered by the participants using strictly COT and BERT judges producing embeddings were trained based on the provided annotation. For an example of BERT embedding visualization and scoring, please refer to https://huggingface.co/turboderp/Cat-Llama-3-70B-instruct
+* Initial support of roleplay as api usage. When roleplaying as an API or function, the model does not produce irrelevant content that's not specified by the system prompt.
+
+# Task coverage
+
+## Chinese tasks on par with English data
+![image/png](1.png)
+For the Chinese portion of the dataset, we strictly kept its distribution and quality comparable to the English counterpart, as visualized by the close distance of the doublets. The overall QC is visualized by PCA after bert embedding
+
+## Individual tasks Quality Checked by doctors
+For each cluster, we QC using BERT embeddings on an umap:
+![image/png](2.png)
+The outliers have been manually checked by doctors.
+
+# Thirdparty dataset
+Thanks to the following people for their tremendous support for dataset generation:
+* steelskull for the medical COT dataset with gpt4o
+* Gryphe for the wonderful action packed dataset
+* Turbca for being turbca
+
+# Prompt format for 8b:
+**llama3**
+Example raw prompt:
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+CatGPT really likes its new cat ears and ends every message with Nyan_<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+CatA: pats CatGPT cat ears<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+CatGPT:
+```
+
+# Prompt format for 72b:
+**chatml**
+Example raw prompt:
+```
+<|im_start|>system 
+CatGPT really likes its new cat ears and ends every message with Nyan_<|im_end|> 
+<|im_start|>user 
+CatA: pats CatGPT cat ears<|im_end|> 
+<|im_start|>assistant
+CatGPT:
+```
+
+# Support
+Please join https://discord.gg/DwGz54Mz for model support

added_tokens.json

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

config.json

@@ -0,0 +1,38 @@
+{
+    "_name_or_path": "models/Qwen2-72B-Instruct",
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "eos_token_id": 151643,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 29568,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 80,
+    "model_type": "qwen2",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 80,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "sliding_window": 131072,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.41.1",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 152064,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.1.7",
+        "bits": 4.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.41.1"
+}

huggingface-metadata.txt

@@ -0,0 +1,9 @@
+url: https://huggingface.co/turboderp/turbcat-instruct-72b-exl2
+branch: 4.0bpw
+download date: 2024-07-19 08:31:25
+sha256sum:
+    529c22edd9da94405cb0c725c105fcb342958e261ae24eedaea6f216d65943d2 output-00001-of-00005.safetensors
+    575205e722e428c69287e5f1bc61c6d6582909e3f52660d585137cfea578e159 output-00002-of-00005.safetensors
+    b4d05d62aba6443da4ea0973dd33cc6a103e38b549c788f562fd497030403640 output-00003-of-00005.safetensors
+    e3c79448b65061313d97c8116d6ebde9b00921451781be4591b046ca609e099f output-00004-of-00005.safetensors
+    046b0d1301bd056ea1ecfa2711b2f3cfa7c89b7567e35155a0716ad799772549 output-00005-of-00005.safetensors

output-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:529c22edd9da94405cb0c725c105fcb342958e261ae24eedaea6f216d65943d2
+size 8512656988

output-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575205e722e428c69287e5f1bc61c6d6582909e3f52660d585137cfea578e159
+size 8581376330

output-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d05d62aba6443da4ea0973dd33cc6a103e38b549c788f562fd497030403640
+size 8495051220

output-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c79448b65061313d97c8116d6ebde9b00921451781be4591b046ca609e099f
+size 8566518504

output-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046b0d1301bd056ea1ecfa2711b2f3cfa7c89b7567e35155a0716ad799772549
+size 4417068700

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}