Duplicate from Replete-AI/Replete-Coder-Qwen2-1.5b

.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 +1,232 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen2-1.5B
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- qwen2
+datasets:
+- Replete-AI/code_bagel_hermes-2.5
+- Replete-AI/code_bagel
+- Replete-AI/OpenHermes-2.5-Uncensored
+- teknium/OpenHermes-2.5
+- layoric/tiny-codes-alpaca
+- glaiveai/glaive-code-assistant-v3
+- ajibawa-2023/Code-290k-ShareGPT
+- TIGER-Lab/MathInstruct
+- chargoddard/commitpack-ft-instruct-rated
+- iamturun/code_instructions_120k_alpaca
+- ise-uiuc/Magicoder-Evol-Instruct-110K
+- cognitivecomputations/dolphin-coder
+- nickrosh/Evol-Instruct-Code-80k-v1
+- coseal/CodeUltraFeedback_binarized
+- glaiveai/glaive-function-calling-v2
+- CyberNative/Code_Vulnerability_Security_DPO
+- jondurbin/airoboros-2.2
+- camel-ai
+- lmsys/lmsys-chat-1m
+- CollectiveCognition/chats-data-2023-09-22
+- CoT-Alpaca-GPT4
+- WizardLM/WizardLM_evol_instruct_70k
+- WizardLM/WizardLM_evol_instruct_V2_196k
+- teknium/GPT4-LLM-Cleaned
+- GPTeacher
+- OpenGPT
+- meta-math/MetaMathQA
+- Open-Orca/SlimOrca
+- garage-bAInd/Open-Platypus
+- anon8231489123/ShareGPT_Vicuna_unfiltered
+- Unnatural-Instructions-GPT4
+model-index:
+- name: Replete-Coder-llama3-8b
+ results:
+ - task:
+ name: HumanEval
+ type: text-generation
+ dataset:
+ type: openai_humaneval
+ name: HumanEval
+ metrics:
+ - name: pass@1
+ type: pass@1
+ value: 0.35365853658536583
+ verified: True
+ - task:
+ name: AI2 Reasoning Challenge
+ type: text-generation
+ dataset:
+ name: AI2 Reasoning Challenge (25-Shot)
+ type: ai2_arc
+ config: ARC-Challenge
+ split: test
+ args:
+ num_few_shot: 25
+ metrics:
+ - type: accuracy
+ value: 
+ name: normalized accuracy
+ source:
+ url: https://www.placeholderurl.com
+ name: Open LLM Leaderboard
+ - task:
+ name: Text Generation
+ type: text-generation
+ dataset:
+ name: HellaSwag (10-Shot)
+ type: hellaswag
+ split: validation
+ args:
+ num_few_shot: 10
+ metrics:
+ - type: accuracy
+ value: 
+ name: normalized accuracy
+ source:
+ url: https://www.placeholderurl.com
+ name: Open LLM Leaderboard
+ - task:
+ name: Text Generation
+ type: text-generation
+ dataset:
+ name: MMLU (5-Shot)
+ type: cais/mmlu
+ config: all
+ split: test
+ args:
+ num_few_shot: 5
+ metrics:
+ - type: accuracy
+ value: 
+ name: accuracy
+ source:
+ url: https://www.placeholderurl.com
+ name: Open LLM Leaderboard
+ - task:
+ name: Text Generation
+ type: text-generation
+ dataset:
+ name: TruthfulQA (0-shot)
+ type: truthful_qa
+ config: multiple_choice
+ split: validation
+ args:
+ num_few_shot: 0
+ metrics:
+ - type: multiple_choice_accuracy
+ value: 
+ source:
+ url: https://www.placeholderurl.com
+ name: Open LLM Leaderboard
+ - task:
+ name: Text Generation
+ type: text-generation
+ dataset:
+ name: Winogrande (5-shot)
+ type: winogrande
+ config: winogrande_xl
+ split: validation
+ args:
+ num_few_shot: 5
+ metrics:
+ - type: accuracy
+ value: 
+ name: accuracy
+ source:
+ url: https://www.placeholderurl.com
+ name: Open LLM Leaderboard
+ - task:
+ name: Text Generation
+ type: text-generation
+ dataset:
+ name: GSM8k (5-shot)
+ type: gsm8k
+ config: main
+ split: test
+ args:
+ num_few_shot: 5
+ metrics:
+ - type: accuracy
+ value: 
+ name: accuracy
+ source:
+ url: https://www.placeholderurl.com
+ name: Open LLM Leaderboard
+
+---
+# Replete-Coder-Qwen2-1.5b
+Finetuned by: Rombodawg
+### More than just a coding model!
+Although Replete-Coder has amazing coding capabilities, its trained on vaste amount of non-coding data, fully cleaned and uncensored. Dont just use it for coding, use it for all your needs! We are truly trying to make the GPT killer!
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/-0dERC793D9XeFsJ9uHbx.png)
+
+Thank you to TensorDock for sponsoring Replete-Coder-llama3-8b and Replete-Coder-Qwen2-1.5b
+you can check out their website for cloud compute rental below. 
+- https://tensordock.com
+__________________________________________________________________________________________________
+Replete-Coder-Qwen2-1.5b is a general purpose model that is specially trained in coding in over 100 coding languages. The data used to train the model contains 25% non-code instruction data and 75% coding instruction data totaling up to 3.9 million lines, roughly 1 billion tokens, or 7.27gb of instruct data. The data used to train this model was 100% uncensored, then fully deduplicated, before training happened.
+
+The Replete-Coder models (including Replete-Coder-llama3-8b and Replete-Coder-Qwen2-1.5b) feature the following:
+
+- Advanced coding capabilities in over 100 coding languages
+- Advanced code translation (between languages)
+- Security and vulnerability prevention related coding capabilities
+- General purpose use
+- Uncensored use
+- Function calling
+- Advanced math use
+- Use on low end (8b) and mobile (1.5b) platforms
+
+Notice: Replete-Coder series of models are fine-tuned on a context window of 8192 tokens. Performance past this context window is not guaranteed.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/JNGVmzaZC30xrvLI1D7pp.png)
+_________________________________________________________________________________________________
+
+You can find the 25% non-coding instruction below:
+
+- https://huggingface.co/datasets/Replete-AI/OpenHermes-2.5-Uncensored
+
+And the 75% coding specific instruction data below:
+
+- https://huggingface.co/datasets/Replete-AI/code_bagel
+
+These two datasets were combined to create the final dataset for training, which is linked below:
+
+- https://huggingface.co/datasets/Replete-AI/code_bagel_hermes-2.5
+__________________________________________________________________________________________________
+## Prompt Template: ChatML
+```
+<|im_start|>system
+{}<|im_end|>
+
+<|im_start|>user
+{}<|im_end|>
+
+<|im_start|>assistant
+{}
+```
+Note: The system prompt varies in training data, but the most commonly used one is:
+```
+Below is an instruction that describes a task, Write a response that appropriately completes the request.
+```
+End token:
+```
+<|endoftext|>
+```
+__________________________________________________________________________________________________
+Thank you to the community for your contributions to the Replete-AI/code_bagel_hermes-2.5 dataset. Without the participation of so many members making their datasets free and open source for any to use, this amazing AI model wouldn't be possible.
+
+Extra special thanks to Teknium for the Open-Hermes-2.5 dataset and jondurbin for the bagel dataset and the naming idea for the code_bagel series of datasets. You can find both of their huggingface accounts linked below:
+
+- https://huggingface.co/teknium
+- https://huggingface.co/jondurbin
+
+Another special thanks to unsloth for being the main method of training for Replete-Coder. Bellow you can find their github, as well as the special Replete-Ai secret sause (Unsloth + Qlora + Galore) colab code document that was used to train this model.
+
+- https://github.com/unslothai/unsloth
+- https://colab.research.google.com/drive/1eXGqy5M--0yW4u0uRnmNgBka-tDk2Li0?usp=sharing
+__________________________________________________________________________________________________
+
+## Join the Replete-Ai discord! We are a great and Loving community!
+
+- https://discord.gg/ZZbnsmVnjD

added_tokens.json

@@ -0,0 +1,6 @@
+{
+ "<|PAD_TOKEN|>": 151646,
+ "<|endoftext|>": 151643,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,30 @@
+{
+ "_name_or_path": "rombodawg/Qwen2-1.5b-Reuploaded",
+ "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": 28,
+ "model_type": "qwen2",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 28,
+ "num_key_value_heads": 2,
+ "pad_token_id": 151646,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 1000000.0,
+ "sliding_window": 131072,
+ "tie_word_embeddings": true,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.41.2",
+ "unsloth_version": "2024.6",
+ "use_cache": true,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+ "bos_token_id": 151643,
+ "eos_token_id": 151643,
+ "max_new_tokens": 2048,
+ "transformers_version": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9af48980efaa5bf239fdc15bfa05ba3ec5bf005419eaf75e1335887f514c45
+size 3087467144

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>"
+ ],
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<|PAD_TOKEN|>"
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+ "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
+ },
+ "151646": {
+ "content": "<|PAD_TOKEN|>",
+ "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": "<|endoftext|>",
+ "errors": "replace",
+ "model_max_length": 131072,
+ "pad_token": "<|PAD_TOKEN|>",
+ "padding_side": "left",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}