README.md

Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


Smaug-Llama-3-70B-Instruct-32K - GGUF
- Model creator: https://huggingface.co/abacusai/
- Original model: https://huggingface.co/abacusai/Smaug-Llama-3-70B-Instruct-32K/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Smaug-Llama-3-70B-Instruct-32K.Q2_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/blob/main/Smaug-Llama-3-70B-Instruct-32K.Q2_K.gguf) | Q2_K | 24.56GB |
| [Smaug-Llama-3-70B-Instruct-32K.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/blob/main/Smaug-Llama-3-70B-Instruct-32K.IQ3_XS.gguf) | IQ3_XS | 27.29GB |
| [Smaug-Llama-3-70B-Instruct-32K.IQ3_S.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/blob/main/Smaug-Llama-3-70B-Instruct-32K.IQ3_S.gguf) | IQ3_S | 28.79GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/blob/main/Smaug-Llama-3-70B-Instruct-32K.Q3_K_S.gguf) | Q3_K_S | 28.79GB |
| [Smaug-Llama-3-70B-Instruct-32K.IQ3_M.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/blob/main/Smaug-Llama-3-70B-Instruct-32K.IQ3_M.gguf) | IQ3_M | 29.74GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q3_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/blob/main/Smaug-Llama-3-70B-Instruct-32K.Q3_K.gguf) | Q3_K | 31.91GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/blob/main/Smaug-Llama-3-70B-Instruct-32K.Q3_K_M.gguf) | Q3_K_M | 31.91GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/blob/main/Smaug-Llama-3-70B-Instruct-32K.Q3_K_L.gguf) | Q3_K_L | 34.59GB |
| [Smaug-Llama-3-70B-Instruct-32K.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/blob/main/Smaug-Llama-3-70B-Instruct-32K.IQ4_XS.gguf) | IQ4_XS | 35.64GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q4_0.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/blob/main/Smaug-Llama-3-70B-Instruct-32K.Q4_0.gguf) | Q4_0 | 37.22GB |
| [Smaug-Llama-3-70B-Instruct-32K.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/tree/main/) | IQ4_NL | 37.58GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/tree/main/) | Q4_K_S | 37.58GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q4_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/tree/main/) | Q4_K | 39.6GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/tree/main/) | Q4_K_M | 39.6GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q4_1.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/tree/main/) | Q4_1 | 41.27GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q5_0.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/tree/main/) | Q5_0 | 45.32GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/tree/main/) | Q5_K_S | 45.32GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q5_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/tree/main/) | Q5_K | 46.52GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/tree/main/) | Q5_K_M | 46.52GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q5_1.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/tree/main/) | Q5_1 | 49.36GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q6_K.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/tree/main/) | Q6_K | 53.91GB |
| [Smaug-Llama-3-70B-Instruct-32K.Q8_0.gguf](https://huggingface.co/RichardErkhov/abacusai_-_Smaug-Llama-3-70B-Instruct-32K-gguf/tree/main/) | Q8_0 | 69.83GB |




Original model description:
---
license: llama3
library_name: transformers
datasets:
- aqua_rat
- microsoft/orca-math-word-problems-200k
- m-a-p/CodeFeedback-Filtered-Instruction
model-index:
- name: Smaug-Llama-3-70B-Instruct-32K
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 77.61
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Llama-3-70B-Instruct-32K
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 49.07
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Llama-3-70B-Instruct-32K
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 21.22
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Llama-3-70B-Instruct-32K
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 6.15
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Llama-3-70B-Instruct-32K
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 12.43
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Llama-3-70B-Instruct-32K
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 41.83
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abacusai/Smaug-Llama-3-70B-Instruct-32K
      name: Open LLM Leaderboard
---

# Smaug-Llama-3-70B-Instruct-32K

### Built with Meta Llama 3

This is a 32K version of Smaug-Llama-3-70B-Instruct. It uses PoSE (https://arxiv.org/abs/2309.10400) and LoRA (https://arxiv.org/abs/2106.09685) adapter transfer. More details are coming soon.

Needle-In-A-Haystack (https://github.com/jzhang38/EasyContext) heatmap:

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/8Z5XgqrZXKcb2hmeTKTT6.png)

### Model Description

- **Developed by:** [Abacus.AI](https://abacus.ai)
- **License:** https://llama.meta.com/llama3/license/
- **Finetuned from model:** [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct).

## How to use

The prompt format is unchanged from Llama 3 70B Instruct.

### Use with transformers

See the snippet below for usage with Transformers:

```python
import transformers
import torch

model_id = "abacusai/Smaug-Llama-3-70B-Instruct"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

prompt = pipeline.tokenizer.apply_chat_template(
		messages, 
		tokenize=False, 
		add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
print(outputs[0]["generated_text"][len(prompt):])
```


## Evaluation

### Arena-Hard

### Arena-Hard

Score vs selected others (sourced from: (https://lmsys.org/blog/2024-04-19-arena-hard/#full-leaderboard-with-gpt-4-turbo-as-judge)). GPT-4o and Gemini-1.5-pro-latest were missing from the original blob post, and we produced those numbers from a local run using the same methodology. 

| Model | Score | 95% Confidence Interval | Average Tokens |
| :---- | ---------: | ----------: | ------: |
| GPT-4-Turbo-2024-04-09 | 82.6  | (-1.8, 1.6)  | 662 |
| GPT-4o | 78.3  | (-2.4, 2.1)  | 685 |
| Gemini-1.5-pro-latest | 72.1  | (-2.3, 2.2)  | 630 |
| Claude-3-Opus-20240229 | 60.4  | (-3.3, 2.4)  | 541 |
| **Smaug-Llama-3-70B-Instruct-32K** | 60.0  | (-2.6, 2.1)  | 844 |
| Smaug-Llama-3-70B-Instruct | 56.7  | (-2.2, 2.6)  | 661 |
| GPT-4-0314 | 50.0  | (-0.0, 0.0)  | 423 |
| Claude-3-Sonnet-20240229 | 46.8  | (-2.1, 2.2)  | 552 |
| Llama-3-70B-Instruct | 41.1  | (-2.5, 2.4)  | 583 |
| GPT-4-0613 | 37.9  | (-2.2, 2.0)  | 354 |
| Mistral-Large-2402 | 37.7 | (-1.9, 2.6)  | 400 |
| Mixtral-8x22B-Instruct-v0.1 | 36.4  | (-2.7, 2.9)  | 430 |
| Qwen1.5-72B-Chat | 36.1 | (-2.5, 2.2)  | 474 |
| Command-R-Plus | 33.1 | (-2.1, 2.2)  | 541 |
| Mistral-Medium | 31.9  | (-2.3, 2.4)  | 485 |
| GPT-3.5-Turbo-0613 | 24.8 | (-1.6, 2.0)  | 401 |

Note that we believe the number of tokens/verbosity of the model strongly influences the GPT-4 judge in this case, and at least partially explains the improvement in Arena-Hard score for the 32K model.

### OpenLLM Leaderboard Manual Evaluation

| Model | ARC  | Hellaswag | MMLU | TruthfulQA | Winogrande | GSM8K* | Average |
| :---- | ---: | ------:   | ---: | ---:       | ---:       | ---:   | ---:   |
| Smaug-Llama-3-70B-Instruct-32K | 70.1 | TBA | TBA | 61.9 | 82.2 | TBA | TBA |
| Llama-3-70B-Instruct | 71.4 | 85.7 | 80.0 | 61.8 | 82.9 | 91.1 | 78.8 |

**GSM8K** The GSM8K numbers quoted here are computed using a recent release
of the [LM Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness/).
The commit used by the leaderboard has a significant issue that impacts models that
tend to use `:` in their responses due to a bug in the stop word configuration for
GSM8K. The issue is covered in more detail in this
[GSM8K evaluation discussion](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard/discussions/770).
The score for both Llama-3 and this model are significantly different when evaluated
with the updated harness as the issue with stop words has been addressed.

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_abacusai__Smaug-Llama-3-70B-Instruct-32K)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |34.72|
|IFEval (0-Shot)    |77.61|
|BBH (3-Shot)       |49.07|
|MATH Lvl 5 (4-Shot)|21.22|
|GPQA (0-shot)      | 6.15|
|MuSR (0-shot)      |12.43|
|MMLU-PRO (5-shot)  |41.83|