Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: other
+datasets:
+- teknium/OpenHermes-2.5
+- LDJnr/Capybara
+- Intel/orca_dpo_pairs
+- argilla/distilabel-capybara-dpo-7k-binarized
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# Quyen
+<img src="quyen.webp" width="512" height="512" alt="Quyen">
+
+# Model Description
+Quyen is our first flagship LLM series based on the Qwen1.5 family. We introduced 6 different versions:
+
+- **Quyen-SE (0.5B)**
+- **Quyen-Mini (1.8B)**
+- **Quyen (4B)**
+- **Quyen-Plus (7B)**
+- **Quyen-Pro (14B)**
+- **Quyen-Pro-Max (72B)**
+
+All models were trained with SFT and DPO using the following dataset:
+
+- *OpenHermes-2.5* by **Teknium**
+- *Capyabara* by **LDJ**
+- *argilla/distilabel-capybara-dpo-7k-binarized* by **argilla**
+- *orca_dpo_pairs* by **Intel**
+- and Private Data by **Ontocord** & **BEE-spoke-data**
+
+# Prompt Template
+- All Quyen models use ChatML as the default template:
+
+```
+<|im_start|>system
+You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
+<|im_start|>user
+Hello world.<|im_end|>
+<|im_start|>assistant
+```
+
+- You can also use `apply_chat_template`:
+
+```python
+messages = [
+    {"role": "system", "content": "You are a sentient, superintelligent artificial general intelligence, here to teach and assist me."},
+    {"role": "user", "content": "Hello world."}
+]
+gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
+model.generate(**gen_input)
+```
+
+# Benchmarks:
+
+- Coming Soon! We will update the benchmarks later
+
+# Acknowledgement
+- We're incredibly grateful to **Tensoic** and **Ontocord** for their generous support with compute and data preparation.
+- Special thanks to the Qwen team for letting us access the models early for these amazing finetunes.

added_tokens.json

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

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "/models/models/Quyen-Mini-v0.1",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 8192,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "modules_to_not_convert": null,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_length": 4096,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "transformers_version": "4.37.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f1ad567040f83e235d335f4b7ccabbdc6fed68f76a46092e505a1aa4225f1e5
+size 1876066752

quant_config.json

@@ -0,0 +1,7 @@
+{
+    "zero_point": true,
+    "q_group_size": 128,
+    "w_bit": 4,
+    "version": "GEMM",
+    "modules_to_not_convert": null
+}

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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": "<|im_end|>",
+  "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
+}