--- inference: false language: - en license: other model_creator: Upstage model_link: https://huggingface.co/upstage/Llama-2-70b-instruct-v2 model_name: Llama 2 70B Instruct v2 model_type: llama pipeline_tag: text-generation quantized_by: TheBloke tags: - upstage - llama-2 - instruct - instruction ---
TheBlokeAI

Chat & support: my new Discord server

Want to contribute? TheBloke's Patreon page

# Llama 2 70B Instruct v2 - GGML - Model creator: [Upstage](https://huggingface.co/Upstage) - Original model: [Llama 2 70B Instruct v2](https://huggingface.co/upstage/Llama-2-70b-instruct-v2) ## Description This repo contains GGML format model files for [Upstage's Llama 2 70B Instruct v2](https://huggingface.co/upstage/Llama-2-70b-instruct-v2). CUDA GPU acceleration is now available for Llama 2 70B GGML files. Metal acceleration (macOS) is not yet available. I haven't tested AMD acceleration - let me know if it owrks. The following clients/libraries are known to work with these files, including with CUDA GPU acceleration: * [llama.cpp](https://github.com/ggerganov/llama.cpp), commit `e76d630` and later. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), version 1.37 and later. A powerful GGML web UI, especially good for story telling. * [LM Studio](https://lmstudio.ai/), a fully featured local GUI with GPU acceleration. (GPU acceleration is Windows only for 70B models at the moment.) * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), version 0.1.77 and later. A Python library with LangChain support, and OpenAI-compatible API server. * [ctransformers](https://github.com/marella/ctransformers), version 0.2.15 and later. A Python library with LangChain support, and OpenAI-compatible API server. ## Repositories available * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGML) * [Upstage's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/upstage/Llama-2-70b-instruct-v2) ## Prompt template: Orca-Hashes ``` ### System: This is a system prompt, please behave and help the user. ### User: {prompt} ### Assistant: ``` ## Compatibility ### Requires llama.cpp [commit `e76d630`](https://github.com/ggerganov/llama.cpp/commit/e76d630df17e235e6b9ef416c45996765d2e36fb) or later. Or one of the other tools and libraries listed above. To use in llama.cpp, you must add `-gqa 8` argument. For other UIs and libraries, please check the docs. ## Explanation of the new k-quant methods
Click to see details The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw * GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type. Refer to the Provided Files table below to see what files use which methods, and how.
## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | [upstage-llama-2-70b-instruct-v2.ggmlv3.q2_K.bin](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGML/blob/main/upstage-llama-2-70b-instruct-v2.ggmlv3.q2_K.bin) | q2_K | 2 | 28.59 GB| 31.09 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. | | [upstage-llama-2-70b-instruct-v2.ggmlv3.q3_K_L.bin](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGML/blob/main/upstage-llama-2-70b-instruct-v2.ggmlv3.q3_K_L.bin) | q3_K_L | 3 | 36.15 GB| 38.65 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | [upstage-llama-2-70b-instruct-v2.ggmlv3.q3_K_M.bin](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGML/blob/main/upstage-llama-2-70b-instruct-v2.ggmlv3.q3_K_M.bin) | q3_K_M | 3 | 33.04 GB| 35.54 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | [upstage-llama-2-70b-instruct-v2.ggmlv3.q3_K_S.bin](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGML/blob/main/upstage-llama-2-70b-instruct-v2.ggmlv3.q3_K_S.bin) | q3_K_S | 3 | 29.75 GB| 32.25 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | | [upstage-llama-2-70b-instruct-v2.ggmlv3.q4_0.bin](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGML/blob/main/upstage-llama-2-70b-instruct-v2.ggmlv3.q4_0.bin) | q4_0 | 4 | 38.87 GB| 41.37 GB | Original quant method, 4-bit. | | [upstage-llama-2-70b-instruct-v2.ggmlv3.q4_1.bin](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGML/blob/main/upstage-llama-2-70b-instruct-v2.ggmlv3.q4_1.bin) | q4_1 | 4 | 43.17 GB| 45.67 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. | | [upstage-llama-2-70b-instruct-v2.ggmlv3.q4_K_M.bin](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGML/blob/main/upstage-llama-2-70b-instruct-v2.ggmlv3.q4_K_M.bin) | q4_K_M | 4 | 41.38 GB| 43.88 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K | | [upstage-llama-2-70b-instruct-v2.ggmlv3.q4_K_S.bin](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGML/blob/main/upstage-llama-2-70b-instruct-v2.ggmlv3.q4_K_S.bin) | q4_K_S | 4 | 38.87 GB| 41.37 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | | [upstage-llama-2-70b-instruct-v2.ggmlv3.q5_0.bin](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGML/blob/main/upstage-llama-2-70b-instruct-v2.ggmlv3.q5_0.bin) | q5_0 | 5 | 47.46 GB| 49.96 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. | | [upstage-llama-2-70b-instruct-v2.ggmlv3.q5_K_M.bin](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGML/blob/main/upstage-llama-2-70b-instruct-v2.ggmlv3.q5_K_M.bin) | q5_K_M | 5 | 48.75 GB| 51.25 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K | | [upstage-llama-2-70b-instruct-v2.ggmlv3.q5_K_S.bin](https://huggingface.co/TheBloke/Upstage-Llama-2-70B-instruct-v2-GGML/blob/main/upstage-llama-2-70b-instruct-v2.ggmlv3.q5_K_S.bin) | q5_K_S | 5 | 47.46 GB| 49.96 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ## How to run in `llama.cpp` I use the following command line; adjust for your tastes and needs: ``` ./main -t 10 -ngl 40 -gqa 8 -m upstage-llama-2-70b-instruct-v2.ggmlv3.q4_K_M.bin --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### System:\nThis is a system prompt, please behave and help the user.\n\n### User:\nWrite a story about llamas\n\n### Assistant:" ``` Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`. Change -ngl 40 to the number of GPU layers you have VRAM for. Use -ngl 100 to offload all layers to VRAM, if you have a 48GB card, or 2 x 24GB, or similar. Otherwise you can partially offload as many as you have VRAM for, on one or more GPUs. Remember the `-gqa 8` argument, required for Llama 70B models. If you want to have a chat-style conversation, replace the `-p ` argument with `-i -ins` ## How to run in `text-generation-webui` Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md). ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute. Thanks to the [chirper.ai](https://chirper.ai) team! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Luke from CarbonQuill, Aemon Algiz. **Patreon special mentions**: Slarti, Chadd, John Detwiler, Pieter, zynix, K, Mano Prime, ReadyPlayerEmma, Ai Maven, Leonard Tan, Edmond Seymore, Joseph William Delisle, Luke @flexchar, Fred von Graf, Viktor Bowallius, Rishabh Srivastava, Nikolai Manek, Matthew Berman, Johann-Peter Hartmann, ya boyyy, Greatston Gnanesh, Femi Adebogun, Talal Aujan, Jonathan Leane, terasurfer, David Flickinger, William Sang, Ajan Kanaga, Vadim, Artur Olbinski, Raven Klaugh, Michael Levine, Oscar Rangel, Randy H, Cory Kujawski, RoA, Dave, Alex, Alexandros Triantafyllidis, Fen Risland, Eugene Pentland, vamX, Elle, Nathan LeClaire, Khalefa Al-Ahmad, Rainer Wilmers, subjectnull, Junyu Yang, Daniel P. Andersen, SuperWojo, LangChain4j, Mandus, Kalila, Illia Dulskyi, Trenton Dambrowitz, Asp the Wyvern, Derek Yates, Jeffrey Morgan, Deep Realms, Imad Khwaja, Pyrater, Preetika Verma, biorpg, Gabriel Tamborski, Stephen Murray, Spiking Neurons AB, Iucharbius, Chris Smitley, Willem Michiel, Luke Pendergrass, Sebastain Graf, senxiiz, Will Dee, Space Cruiser, Karl Bernard, Clay Pascal, Lone Striker, transmissions 11, webtim, WelcomeToTheClub, Sam, theTransient, Pierre Kircher, chris gileta, John Villwock, Sean Connelly, Willian Hasse Thank you to all my generous patrons and donaters! # Original model card: Upstage's Llama 2 70B Instruct v2 # LLaMa-2-70b-instruct-v2 model card ## Model Details * **Developed by**: [Upstage](https://en.upstage.ai) * **Backbone Model**: [LLaMA-2](https://github.com/facebookresearch/llama/tree/main) * **Language(s)**: English * **Library**: [HuggingFace Transformers](https://github.com/huggingface/transformers) * **License**: Fine-tuned checkpoints is licensed under the Non-Commercial Creative Commons license ([CC BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/)) * **Where to send comments**: Instructions on how to provide feedback or comments on a model can be found by opening an issue in the [Hugging Face community's model repository](https://huggingface.co/upstage/Llama-2-70b-instruct-v2/discussions) * **Contact**: For questions and comments about the model, please email [contact@upstage.ai](mailto:contact@upstage.ai) ## Dataset Details ### Used Datasets - Orca-style dataset - Alpaca-Style Dataset ### Prompt Template ``` ### System: {System} ### User: {User} ### Assistant: {Assistant} ``` ### Usage *Tested on A100 80GB* ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer tokenizer = AutoTokenizer.from_pretrained("upstage/Llama-2-70b-instruct-v2") model = AutoModelForCausalLM.from_pretrained( "upstage/Llama-2-70b-instruct-v2", device_map='auto', torch_dtype=torch.float16, load_in_8bit=True, rope_scaling={'type': 'dynamic', 'factor': 2} # longer inputs possible ) prompt = "### User:\nThomas is very healthy, but he has to go to the hospital every day. What could be the reasons?\n\n### Assistant:\n" inputs = tokenizer(prompt, return_tensors="pt").to(model.device) del inputs['token_type_ids'] streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) output = model.generate(**inputs, streamer=streamer, use_cache=True, max_new_tokens=float('inf')) output_text = tokenizer.decode(output[0], skip_prompt=True, skip_special_tokens=True) ``` **Our model can handle >10k input tokens thanks to the `rope_scaling` option.** ## Hardware and Software * **Hardware**: We utilized an A100x8 * 4 for training our model * **Training Factors**: We fine-tuned this model using a combination of the [DeepSpeed library](https://github.com/microsoft/DeepSpeed) and the [HuggingFace trainer](https://huggingface.co/docs/transformers/main_classes/trainer) / [HuggingFace Accelerate](https://huggingface.co/docs/accelerate/index) ## Evaluation Results ### Overview - We conducted a performance evaluation based on the tasks being evaluated on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). We evaluated our model on four benchmark datasets, which include `ARC-Challenge`, `HellaSwag`, `MMLU`, and `TruthfulQA`. We used the [lm-evaluation-harness repository](https://github.com/EleutherAI/lm-evaluation-harness), specifically commit [b281b0921b636bc36ad05c0b0b0763bd6dd43463](https://github.com/EleutherAI/lm-evaluation-harness/tree/b281b0921b636bc36ad05c0b0b0763bd6dd43463). ### Main Results | Model | H4 Average | ARC | HellaSwag | MMLU | TruthfulQA | | MT_Bench | |-----------------------------------------------|---------|-------|-----------|-------|------------|-------|----------| | **Llama-2-70b-instruct-v2** (***Ours***, ***Local Reproduction***) | **72.7** | **71.6** | **87.7** | **69.7** | **61.6** | | 7.440625 | | Llama-2-70b-instruct (Ours, Local Reproduction) | 72.0 | 70.7 | 87.4 | 69.3 | 60.7 | | 7.24375 | | llama-65b-instruct (Ours, Local Reproduction) | 69.4 | 67.6 | 86.5 | 64.9 | 58.8 | | | | Llama-2-70b-hf | 67.3 | 67.3 | 87.3 | 69.8 | 44.9 | | | | llama-30b-instruct-2048 (Ours, Open LLM Leaderboard) | 67.0 | 64.9 | 84.9 | 61.9 | 56.3 | | | | llama-30b-instruct-2048 (Ours, Local Reproduction) | 67.0 | 64.9 | 85.0 | 61.9 | 56.0 | | 6.88125 | | llama-30b-instruct (Ours, Open LLM Leaderboard) | 65.2 | 62.5 | 86.2 | 59.4 | 52.8 | | | | llama-65b | 64.2 | 63.5 | 86.1 | 63.9 | 43.4 | | | | falcon-40b-instruct | 63.4 | 61.6 | 84.3 | 55.4 | 52.5 | | | ### Scripts - Prepare evaluation environments: ``` # clone the repository git clone https://github.com/EleutherAI/lm-evaluation-harness.git # check out the specific commit git checkout b281b0921b636bc36ad05c0b0b0763bd6dd43463 # change to the repository directory cd lm-evaluation-harness ``` ## Ethical Issues ### Ethical Considerations - There were no ethical issues involved, as we did not include the benchmark test set or the training set in the model's training process. ## Contact Us ### Why Upstage LLM? - [Upstage](https://en.upstage.ai)'s LLM research has yielded remarkable results. Our 30B model **outperforms all models around the world**, positioning itself as the leading performer. Recognizing the immense potential in implementing private LLM to actual businesses, we invite you to easily apply private LLM and fine-tune it with your own data. For a seamless and tailored solution, please do not hesitate to reach out to us. ► [click here to contact](https://www.upstage.ai/private-llm?utm_source=huggingface&utm_medium=link&utm_campaign=privatellm).