RichardErkhov/Sharathhebbar24_-_code_gpt2-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

code_gpt2 - GGUF

• Model creator: https://huggingface.co/Sharathhebbar24/
• Original model: https://huggingface.co/Sharathhebbar24/code_gpt2/

Name	Quant method	Size
code_gpt2.Q2_K.gguf	Q2_K	0.08GB
code_gpt2.IQ3_XS.gguf	IQ3_XS	0.08GB
code_gpt2.IQ3_S.gguf	IQ3_S	0.08GB
code_gpt2.Q3_K_S.gguf	Q3_K_S	0.08GB
code_gpt2.IQ3_M.gguf	IQ3_M	0.09GB
code_gpt2.Q3_K.gguf	Q3_K	0.09GB
code_gpt2.Q3_K_M.gguf	Q3_K_M	0.09GB
code_gpt2.Q3_K_L.gguf	Q3_K_L	0.1GB
code_gpt2.IQ4_XS.gguf	IQ4_XS	0.1GB
code_gpt2.Q4_0.gguf	Q4_0	0.1GB
code_gpt2.IQ4_NL.gguf	IQ4_NL	0.1GB
code_gpt2.Q4_K_S.gguf	Q4_K_S	0.1GB
code_gpt2.Q4_K.gguf	Q4_K	0.11GB
code_gpt2.Q4_K_M.gguf	Q4_K_M	0.11GB
code_gpt2.Q4_1.gguf	Q4_1	0.11GB
code_gpt2.Q5_0.gguf	Q5_0	0.11GB
code_gpt2.Q5_K_S.gguf	Q5_K_S	0.11GB
code_gpt2.Q5_K.gguf	Q5_K	0.12GB
code_gpt2.Q5_K_M.gguf	Q5_K_M	0.12GB
code_gpt2.Q5_1.gguf	Q5_1	0.12GB
code_gpt2.Q6_K.gguf	Q6_K	0.13GB
code_gpt2.Q8_0.gguf	Q8_0	0.17GB

Original model description:

language: - en license: apache-2.0 tags: - gpt2 - dpo - code datasets: - HuggingFaceH4/ultrachat_200k - mlabonne/CodeLlama-2-20k - Intel/orca_dpo_pairs - Sharathhebbar24/Evol-Instruct-Code-80k-v1 - Sharathhebbar24/sql-create-context pipeline_tag: text-generation model-index: - name: code_gpt2 results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 23.29 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/code_gpt2 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 30.99 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/code_gpt2 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 25.03 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/code_gpt2 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 40.6 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/code_gpt2 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 49.25 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/code_gpt2 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 0.0 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/code_gpt2 name: Open LLM Leaderboard

This model is a finetuned version of Sharathhebbar24/code_gpt2_mini_model using Sharathhebbar24/Evol-Instruct-Code-80k-v1

Model description

GPT-2 is a transformers model pre-trained on a very large corpus of English data in a self-supervised fashion. This means it was pre-trained on the raw texts only, with no humans labeling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was trained to guess the next word in sentences.

More precisely, inputs are sequences of continuous text of a certain length and the targets are the same sequence, shifting one token (word or piece of word) to the right. The model uses a masking mechanism to make sure the predictions for the token i only use the inputs from 1 to i but not the future tokens.

This way, the model learns an inner representation of the English language that can then be used to extract features useful for downstream tasks. The model is best at what it was trained for, however, which is generating texts from a prompt.

To use this model

>>> from transformers import AutoTokenizer, AutoModelForCausalLM
>>> model_name = "Sharathhebbar24/code_gpt2"
>>> model = AutoModelForCausalLM.from_pretrained(model_name)
>>> tokenizer = AutoTokenizer.from_pretrained(model_name)
>>> def generate_text(prompt):
>>>  inputs = tokenizer.encode(prompt, return_tensors='pt')
>>>  outputs = model.generate(inputs, max_length=64, pad_token_id=tokenizer.eos_token_id)
>>>  generated = tokenizer.decode(outputs[0], skip_special_tokens=True)
>>>  return generated[:generated.rfind(".")+1]
>>> prompt = "Can you write a Linear search program in Python"
>>> res = generate_text(prompt)
>>> res

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	28.19
AI2 Reasoning Challenge (25-Shot)	23.29
HellaSwag (10-Shot)	30.99
MMLU (5-Shot)	25.03
TruthfulQA (0-shot)	40.60
Winogrande (5-shot)	49.25
GSM8k (5-shot)	0.00