DBMe
/

Llama-3.1-Nemotron-70B-Instruct-HF-4.6bpw-h6-exl2

@@ -13,182 +13,21 @@ base_model: meta-llama/Llama-3.1-70B-Instruct
 pipeline_tag: text-generation
 library_name: transformers
 ---
-# Model Overview
-## Description:
-Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.
-This model reaches [Arena Hard](https://github.com/lmarena/arena-hard-auto) of 85.0, [AlpacaEval 2 LC](https://tatsu-lab.github.io/alpaca_eval/) of 57.6 and [GPT-4-Turbo MT-Bench](https://github.com/lm-sys/FastChat/pull/3158) of 8.98, which are known to be predictive of [LMSys Chatbot Arena Elo](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard)
-As of 1 Oct 2024, this model is #1 on all three automatic alignment benchmarks (verified tab for AlpacaEval 2 LC), edging out strong frontier models such as GPT-4o and Claude 3.5 Sonnet.
-This model was trained using RLHF (specifically, REINFORCE), [Llama-3.1-Nemotron-70B-Reward](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Reward) and [HelpSteer2-Preference prompts](https://huggingface.co/datasets/nvidia/HelpSteer2) on a Llama-3.1-70B-Instruct model as the initial policy.
-Llama-3.1-Nemotron-70B-Instruct-HF has been converted from [Llama-3.1-Nemotron-70B-Instruct](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct) to support it in the HuggingFace Transformers codebase. Please note that evaluation results might be slightly different from the [Llama-3.1-Nemotron-70B-Instruct](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct) as evaluated in NeMo-Aligner, which the evaluation results below are based on.
-Try hosted inference for free at [build.nvidia.com](https://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-instruct) - it comes with an OpenAI-compatible API interface.
-See details on our paper at [https://arxiv.org/abs/2410.01257](https://arxiv.org/abs/2410.01257) - as a preview, this model can correctly the question ```How many r in strawberry?``` without specialized prompting or additional reasoning tokens:
-```
-A sweet question!
-Let’s count the “R”s in “strawberry”:
-1. S
-2. T
-3. R
-4. A
-5. W
-6. B
-7. E
-8. R
-9. R
-10. Y
-There are **3 “R”s** in the word “strawberry”.
-```
-Note: This model is a demonstration of our techniques for improving helpfulness in general-domain instruction following. It has not been tuned for performance in specialized domains such as math.
-## Terms of use
-By accessing this model, you are agreeing to the LLama 3.1 terms and conditions of the [license](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE), [acceptable use policy](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/USE_POLICY.md) and [Meta’s privacy policy](https://www.facebook.com/privacy/policy/)
-## Evaluation Metrics
-As of 1 Oct 2024, Llama-3.1-Nemotron-70B-Instruct performs best on Arena Hard, AlpacaEval 2 LC (verified tab) and MT Bench (GPT-4-Turbo)
- | Model  | Arena Hard | AlpacaEval | MT-Bench | Mean Response Length |
-|:-----------------------------|:----------------|:-----|:----------|:-------|
-|Details | (95% CI) | 2 LC (SE) | (GPT-4-Turbo) | (# of Characters for MT-Bench)|
-| _**Llama-3.1-Nemotron-70B-Instruct**_ | **85.0** (-1.5, 1.5) | **57.6** (1.65) | **8.98** | 2199.8 |
-| Llama-3.1-70B-Instruct | 55.7 (-2.9, 2.7) | 38.1 (0.90)  | 8.22 | 1728.6 |
-| Llama-3.1-405B-Instruct | 69.3 (-2.4, 2.2) | 39.3 (1.43) | 8.49 | 1664.7 |
-| Claude-3-5-Sonnet-20240620 | 79.2 (-1.9, 1.7) | 52.4 (1.47) | 8.81 | 1619.9 |
-| GPT-4o-2024-05-13 | 79.3 (-2.1, 2.0) | 57.5 (1.47) | 8.74 | 1752.2 |
-## Usage:
-You can use the model using HuggingFace Transformers library with 2 or more 80GB GPUs (NVIDIA Ampere or newer) with at least 150GB of free disk space to accomodate the download.
-This code has been tested on Transformers v4.44.0, torch v2.4.0 and 2 A100 80GB GPUs, but any setup that supports ```meta-llama/Llama-3.1-70B-Instruct``` should support this model as well. If you run into problems, you can consider doing ```pip install -U transformers```.
-```python
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-model_name = "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF"
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-prompt = "How many r in strawberry?"
-messages = [{"role": "user", "content": prompt}]
-tokenized_message = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)
-response_token_ids = model.generate(tokenized_message['input_ids'].cuda(),attention_mask=tokenized_message['attention_mask'].cuda(),  max_new_tokens=4096, pad_token_id = tokenizer.eos_token_id)
-generated_tokens =response_token_ids[:, len(tokenized_message['input_ids'][0]):]
-generated_text = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]
-print(generated_text)
-# See response at top of model card
-```
-## Contact
-E-Mail: [Zhilin Wang](mailto:zhilinw@nvidia.com)
-## Citation
-If you find this model useful, please cite the following works
-```bibtex
-@misc{wang2024helpsteer2preferencecomplementingratingspreferences,
-      title={HelpSteer2-Preference: Complementing Ratings with Preferences},
-      author={Zhilin Wang and Alexander Bukharin and Olivier Delalleau and Daniel Egert and Gerald Shen and Jiaqi Zeng and Oleksii Kuchaiev and Yi Dong},
-      year={2024},
-      eprint={2410.01257},
-      archivePrefix={arXiv},
-      primaryClass={cs.LG},
-      url={https://arxiv.org/abs/2410.01257},
-}
-@misc{wang2024helpsteer2,
-      title={HelpSteer2: Open-source dataset for training top-performing reward models},
-      author={Zhilin Wang and Yi Dong and Olivier Delalleau and Jiaqi Zeng and Gerald Shen and Daniel Egert and Jimmy J. Zhang and Makesh Narsimhan Sreedhar and Oleksii Kuchaiev},
-      year={2024},
-      eprint={2406.08673},
-      archivePrefix={arXiv},
-      primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'}
-}
-```
-## References(s):
-* [HelpSteer2-Preference](https://arxiv.org/abs/2410.01257)
-* [SteerLM method](https://arxiv.org/abs/2310.05344)
-* [HelpSteer](https://arxiv.org/abs/2311.09528)
-* [HelpSteer2](https://arxiv.org/abs/2406.08673)
-* [Introducing Llama 3.1: Our most capable models to date](https://ai.meta.com/blog/meta-llama-3-1/)
-* [Meta's Llama 3.1 Webpage](https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_1)
-* [Meta's Llama 3.1 Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md)
-## Model Architecture:
-**Architecture Type:** Transformer <br>
-**Network Architecture:** Llama 3.1 <br>
-## Input:
-**Input Type(s):** Text <br>
-**Input Format:** String <br>
-**Input Parameters:** One Dimensional (1D) <br>
-**Other Properties Related to Input:** Max of 128k tokens<br>
-## Output:
-**Output Type(s):** Text <br>
-**Output Format:** String <br>
-**Output Parameters:** One Dimensional (1D) <br>
-**Other Properties Related to Output:**  Max of 4k tokens <br>
-## Software Integration:
-**Supported Hardware Microarchitecture Compatibility:** <br>
-* NVIDIA Ampere <br>
-* NVIDIA Hopper <br>
-* NVIDIA Turing <br>
-**Supported Operating System(s):** Linux <br>
-## Model Version:
-v1.0
-# Training & Evaluation:
-## Datasets:
-**Data Collection Method by dataset** <br>
-* [Hybrid: Human, Synthetic] <br>
-**Labeling Method by dataset** <br>
-* [Human] <br>
-**Link:**
-* [HelpSteer2](https://huggingface.co/datasets/nvidia/HelpSteer2)
-**Properties (Quantity, Dataset Descriptions, Sensor(s)):** <br>
-* 21, 362 prompt-responses built to make more models more aligned with human preference - specifically more helpful, factually-correct, coherent, and customizable based on complexity and verbosity.
-* 20, 324 prompt-responses used for training and 1, 038 used for validation.
-# Inference:
-**Engine:** [Triton](https://developer.nvidia.com/triton-inference-server) <br>
-**Test Hardware:** H100, A100 80GB, A100 40GB <br>
-## Ethical Considerations:
-NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications.  When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.  For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards.  Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
-Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).

 pipeline_tag: text-generation
 library_name: transformers
 ---
+Quantized model => https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
+**Quantization Details:**
+Quantization is done using turboderp's ExLlamaV2 v0.2.2.
+I use the default calibration datasets and arguments. The repo also includes a "measurement.json" file, which was used during the quantization process.
+For models with bits per weight (BPW) over 6.0, I default to quantizing the `lm_head` layer at 8 bits instead of the standard 6 bits.
+---
+**Who are you? What's with these weird BPWs on [insert model here]?**
+I specialize in optimized EXL2 quantization for models in the 70B to 100B+ range, specifically tailored for 48GB VRAM setups. My rig is built using 2 x 3090s with a Ryzen APU (APU used solely for desktop output—no VRAM wasted on the 3090s). I use TabbyAPI for inference, targeting context sizes between 32K and 64K.
+Every model I upload includes a `config.yml` file with my ideal TabbyAPI settings. If you're using my config, don’t forget to set `PYTORCH_CUDA_ALLOC_CONF=backend:cudaMallocAsync` to save some VRAM.