You can deploy this model and start earning money today!

RichardErkhov/
mediocredev_-_open-llama-3b-v2-chat-gguf

Name: mediocredev_-_open-llama-3b-v2-chat-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

open-llama-3b-v2-chat - GGUF

Model creator: https://huggingface.co/mediocredev/
Original model: https://huggingface.co/mediocredev/open-llama-3b-v2-chat/

Name	Quant method	Size
open-llama-3b-v2-chat.Q2_K.gguf	Q2_K	1.84GB
open-llama-3b-v2-chat.IQ3_XS.gguf	IQ3_XS	1.84GB
open-llama-3b-v2-chat.IQ3_S.gguf	IQ3_S	1.84GB
open-llama-3b-v2-chat.Q3_K_S.gguf	Q3_K_S	1.84GB
open-llama-3b-v2-chat.IQ3_M.gguf	IQ3_M	1.92GB
open-llama-3b-v2-chat.Q3_K.gguf	Q3_K	1.99GB
open-llama-3b-v2-chat.Q3_K_M.gguf	Q3_K_M	1.99GB
open-llama-3b-v2-chat.Q3_K_L.gguf	Q3_K_L	2.06GB
open-llama-3b-v2-chat.IQ4_XS.gguf	IQ4_XS	1.86GB
open-llama-3b-v2-chat.Q4_0.gguf	Q4_0	1.84GB
open-llama-3b-v2-chat.IQ4_NL.gguf	IQ4_NL	1.86GB
open-llama-3b-v2-chat.Q4_K_S.gguf	Q4_K_S	2.24GB
open-llama-3b-v2-chat.Q4_K.gguf	Q4_K	2.4GB
open-llama-3b-v2-chat.Q4_K_M.gguf	Q4_K_M	2.4GB
open-llama-3b-v2-chat.Q4_1.gguf	Q4_1	2.04GB
open-llama-3b-v2-chat.Q5_0.gguf	Q5_0	2.23GB
open-llama-3b-v2-chat.Q5_K_S.gguf	Q5_K_S	2.42GB
open-llama-3b-v2-chat.Q5_K.gguf	Q5_K	2.57GB
open-llama-3b-v2-chat.Q5_K_M.gguf	Q5_K_M	2.57GB
open-llama-3b-v2-chat.Q5_1.gguf	Q5_1	2.42GB
open-llama-3b-v2-chat.Q6_K.gguf	Q6_K	3.39GB
open-llama-3b-v2-chat.Q8_0.gguf	Q8_0	3.39GB

Original model description:

license: apache-2.0 model-index:

name: open-llama-3b-v2-chat 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: 40.61 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mediocredev/open-llama-3b-v2-chat 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: 70.3 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mediocredev/open-llama-3b-v2-chat 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: 28.73 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mediocredev/open-llama-3b-v2-chat 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: 37.84 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mediocredev/open-llama-3b-v2-chat 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: 65.51 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mediocredev/open-llama-3b-v2-chat 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: 2.58 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mediocredev/open-llama-3b-v2-chat name: Open LLM Leaderboard

Prerequisites

In addition to pytorch and transformers, install required packages:

pip install sentencepiece

Usage

To use, copy the following script:

python

ffrom transformers import AutoModelForCausalLM, AutoTokenizer

model_id = 'mediocredev/open-llama-3b-v2-chat'
tokenizer_id = 'mediocredev/open-llama-3b-v2-chat'
tokenizer = AutoTokenizer.from_pretrained(tokenizer_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

chat_history = [
    {"role": "user", "content": "Hello!"},
    {"role": "assistant", "content": "I am here."},
    {"role": "user", "content": "How many days are there in a leap year?"},
]

input_ids = tokenizer.apply_chat_template(
    chat_history, tokenize=True, add_generation_prompt=True, return_tensors="pt"
).to(model.device)
output_tokens = model.generate(
    input_ids,
    repetition_penalty=1.05,
    max_new_tokens=1000,
)
output_text = tokenizer.decode(
    output_tokens[0][len(input_ids[0]) :], skip_special_tokens=True
)

print(output_text)
# Assistant: There are 366 days in a leap year, which is one more day than the standard year.

Limitations

mediocredev/open-llama-3b-v2-chat is based on LLaMA 3B v2. It can struggle with factual accuracy, particularly when presented with conflicting information or nuanced topics. Its outputs are not deterministic and require critical evaluation to avoid relying solely on its assertions. Additionally, its generative capabilities, while promising, can sometimes produce factually incorrect or offensive content, necessitating careful curation and human oversight. As an evolving model, LLaMA is still under development, and its limitations in areas like bias mitigation and interpretability are being actively addressed. By using this model responsibly and being aware of its shortcomings, we can unlock its potential while mitigating its risks.

Contact

Welcome any feedback, questions, and discussions. Feel free to reach out: mediocredev@outlook.com

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	40.93
AI2 Reasoning Challenge (25-Shot)	40.61
HellaSwag (10-Shot)	70.30
MMLU (5-Shot)	28.73
TruthfulQA (0-shot)	37.84
Winogrande (5-shot)	65.51
GSM8k (5-shot)	2.58

RichardErkhov/mediocredev_-_open-llama-3b-v2-chat-gguf