Upload folder using huggingface_hub

README.md

@@ -0,0 +1,414 @@
+
+---
+tags:
+- generated_from_trainer
+license: mit
+datasets:
+- HuggingFaceH4/ultrachat_200k
+- HuggingFaceH4/ultrafeedback_binarized
+language:
+- en
+base_model: mistralai/Mistral-7B-v0.1
+widget:
+  - text: "<|system|>\nYou are a pirate chatbot who always responds with Arr!</s>\n<|user|>\nThere's a llama on my lawn, how can I get rid of him?</s>\n<|assistant|>\n"
+    output:
+      text: "Arr! 'Tis a puzzlin' matter, me hearty! A llama on yer lawn be a rare sight, but I've got a plan that might help ye get rid of 'im. Ye'll need to gather some carrots and hay, and then lure the llama away with the promise of a tasty treat. Once he's gone, ye can clean up yer lawn and enjoy the peace and quiet once again. But beware, me hearty, for there may be more llamas where that one came from! Arr!"
+pipeline_tag: text-generation
+model-index:
+- name: zephyr-7b-beta
+  results:
+  # AI2 Reasoning Challenge (25-Shot)
+  - 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
+         name: normalized accuracy
+         value: 0.6203071672354948
+    source:
+      name: Open LLM Leaderboard
+      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
+
+  # HellaSwag (10-shot)
+  - 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
+         name: normalized accuracy
+         value: 0.8435570603465445
+    source:
+      name: Open LLM Leaderboard
+      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
+
+  # DROP (3-shot)
+  - task: 
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Drop (3-Shot)
+      type: drop
+      split: validation
+      args:
+        num_few_shot: 3
+    metrics:
+       - type: f1
+         name: f1 score
+         value: 0.09662437080536909
+    source:
+      name: Open LLM Leaderboard
+      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
+
+  # TruthfulQA (0-shot)
+  - 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: 0.5744916942762855
+    source:
+      name: Open LLM Leaderboard
+      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
+
+  # GSM8k (5-shot)
+  - 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
+         name: accuracy
+         value: 0.12736921910538287
+    source:
+      name: Open LLM Leaderboard
+      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
+
+  # MMLU (5-Shot)
+  - 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
+         name: accuracy
+         value: 0.6107
+    source:
+      name: Open LLM Leaderboard
+      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
+
+  # Winogrande (5-shot)
+  - 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
+         name: accuracy
+         value: 0.7774269928966061
+    source:
+      name: Open LLM Leaderboard
+      url: https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta_public
+
+  # AlpacaEval (taken from model card)
+  - task: 
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AlpacaEval
+      type: tatsu-lab/alpaca_eval
+    metrics:
+       - type: unknown
+         name: win rate
+         value: 0.9060
+    source:
+      url: https://tatsu-lab.github.io/alpaca_eval/
+
+  # MT-Bench (taken from model card)
+  - task: 
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MT-Bench
+      type: unknown
+    metrics:
+       - type: unknown
+         name: score
+         value: 7.34
+    source:
+      url: https://huggingface.co/spaces/lmsys/mt-bench
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+<img src="https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/resolve/main/thumbnail.png" alt="Zephyr Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
+
+
+# Model Card for Zephyr 7B β
+
+This is a wasm quantized version of zephyr 7b beta. 
+Compiled by using [mlc-llm](https://github.com/mlc-ai/mlc-llm)
+
+Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) that was trained on on a mix of publicly available, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290). We found that removing the in-built alignment of these datasets boosted performance on [MT Bench](https://huggingface.co/spaces/lmsys/mt-bench) and made the model more helpful. However, this means that model is likely to generate problematic text when prompted to do so. You can find more details in the [technical report](https://arxiv.org/abs/2310.16944).
+
+
+## Model description
+
+- **Model type:** A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
+- **Language(s) (NLP):** Primarily English
+- **License:** MIT
+- **Finetuned from model:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
+
+### Model Sources
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** https://github.com/huggingface/alignment-handbook
+- **Demo:** https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat
+- **Chatbot Arena:** Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: http://arena.lmsys.org
+
+## Performance
+
+At the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the [MT-Bench](https://huggingface.co/spaces/lmsys/mt-bench) and [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmarks:
+
+| Model | Size | Alignment | MT-Bench (score) | AlpacaEval (win rate %) |
+|-------------|-----|----|---------------|--------------|
+| StableLM-Tuned-α | 7B| dSFT |2.75| -|
+| MPT-Chat |  7B |dSFT |5.42| -|
+| Xwin-LMv0.1 | 7B| dPPO| 6.19| 87.83|
+| Mistral-Instructv0.1 | 7B|  - | 6.84 |-|
+| Zephyr-7b-α |7B|  dDPO| 6.88| -|
+| **Zephyr-7b-β** 🪁 | **7B** | **dDPO** | **7.34** | **90.60** |
+| Falcon-Instruct |  40B |dSFT |5.17 |45.71|
+| Guanaco | 65B |  SFT |6.41| 71.80|
+| Llama2-Chat |  70B |RLHF |6.86| 92.66|
+| Vicuna v1.3 |  33B |dSFT |7.12 |88.99|
+| WizardLM v1.0 |  70B |dSFT |7.71 |-|
+| Xwin-LM v0.1 |   70B |dPPO |- |95.57|
+| GPT-3.5-turbo | - |RLHF |7.94 |89.37|
+| Claude 2 |  - |RLHF |8.06| 91.36|
+| GPT-4 |  -| RLHF |8.99| 95.28|
+
+In particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6200d0a443eb0913fa2df7cc/raxvt5ma16d7T23my34WC.png)
+
+However, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.
+
+
+## Intended uses & limitations
+
+The model was initially fine-tuned on a filtered and preprocessed of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. 
+We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our [demo](https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat) to test its capabilities. 
+
+You can find the datasets used for training Zephyr-7B-β [here](https://huggingface.co/collections/HuggingFaceH4/zephyr-7b-6538c6d6d5ddd1cbb1744a66)
+
+Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
+
+```python
+# Install transformers from source - only needed for versions <= v4.34
+# pip install git+https://github.com/huggingface/transformers.git
+# pip install accelerate
+
+import torch
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-beta", torch_dtype=torch.bfloat16, device_map="auto")
+
+# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
+messages = [
+    {
+        "role": "system",
+        "content": "You are a friendly chatbot who always responds in the style of a pirate",
+    },
+    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
+]
+prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+# <|system|>
+# You are a friendly chatbot who always responds in the style of a pirate.</s>
+# <|user|>
+# How many helicopters can a human eat in one sitting?</s>
+# <|assistant|>
+# Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!
+```
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+Zephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). 
+It is also unknown what the size and composition of the corpus was used to train the base model (`mistralai/Mistral-7B-v0.1`), however it is likely to have included a mix of Web data and technical sources like books and code. See the [Falcon 180B model card](https://huggingface.co/tiiuae/falcon-180B#training-data) for an example of this.
+
+
+## Training and evaluation data
+
+During DPO training, this model achieves the following results on the evaluation set:
+
+- Loss: 0.7496
+- Rewards/chosen: -4.5221
+- Rewards/rejected: -8.3184
+- Rewards/accuracies: 0.7812
+- Rewards/margins: 3.7963
+- Logps/rejected: -340.1541
+- Logps/chosen: -299.4561
+- Logits/rejected: -2.3081
+- Logits/chosen: -2.3531
+
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 2
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- total_train_batch_size: 32
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+The table below shows the full set of DPO training metrics:
+
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.6284        | 0.05  | 100  | 0.6098          | 0.0425         | -0.1872          | 0.7344             | 0.2297          | -258.8416      | -253.8099    | -2.7976         | -2.8234       |
+| 0.4908        | 0.1   | 200  | 0.5426          | -0.0279        | -0.6842          | 0.75               | 0.6563          | -263.8124      | -254.5145    | -2.7719         | -2.7960       |
+| 0.5264        | 0.15  | 300  | 0.5324          | 0.0414         | -0.9793          | 0.7656             | 1.0207          | -266.7627      | -253.8209    | -2.7892         | -2.8122       |
+| 0.5536        | 0.21  | 400  | 0.4957          | -0.0185        | -1.5276          | 0.7969             | 1.5091          | -272.2460      | -254.4203    | -2.8542         | -2.8764       |
+| 0.5362        | 0.26  | 500  | 0.5031          | -0.2630        | -1.5917          | 0.7812             | 1.3287          | -272.8869      | -256.8653    | -2.8702         | -2.8958       |
+| 0.5966        | 0.31  | 600  | 0.5963          | -0.2993        | -1.6491          | 0.7812             | 1.3499          | -273.4614      | -257.2279    | -2.8778         | -2.8986       |
+| 0.5014        | 0.36  | 700  | 0.5382          | -0.2859        | -1.4750          | 0.75               | 1.1891          | -271.7204      | -257.0942    | -2.7659         | -2.7869       |
+| 0.5334        | 0.41  | 800  | 0.5677          | -0.4289        | -1.8968          | 0.7969             | 1.4679          | -275.9378      | -258.5242    | -2.7053         | -2.7265       |
+| 0.5251        | 0.46  | 900  | 0.5772          | -0.2116        | -1.3107          | 0.7344             | 1.0991          | -270.0768      | -256.3507    | -2.8463         | -2.8662       |
+| 0.5205        | 0.52  | 1000 | 0.5262          | -0.3792        | -1.8585          | 0.7188             | 1.4793          | -275.5552      | -258.0276    | -2.7893         | -2.7979       |
+| 0.5094        | 0.57  | 1100 | 0.5433          | -0.6279        | -1.9368          | 0.7969             | 1.3089          | -276.3377      | -260.5136    | -2.7453         | -2.7536       |
+| 0.5837        | 0.62  | 1200 | 0.5349          | -0.3780        | -1.9584          | 0.7656             | 1.5804          | -276.5542      | -258.0154    | -2.7643         | -2.7756       |
+| 0.5214        | 0.67  | 1300 | 0.5732          | -1.0055        | -2.2306          | 0.7656             | 1.2251          | -279.2761      | -264.2903    | -2.6986         | -2.7113       |
+| 0.6914        | 0.72  | 1400 | 0.5137          | -0.6912        | -2.1775          | 0.7969             | 1.4863          | -278.7448      | -261.1467    | -2.7166         | -2.7275       |
+| 0.4655        | 0.77  | 1500 | 0.5090          | -0.7987        | -2.2930          | 0.7031             | 1.4943          | -279.8999      | -262.2220    | -2.6651         | -2.6838       |
+| 0.5731        | 0.83  | 1600 | 0.5312          | -0.8253        | -2.3520          | 0.7812             | 1.5268          | -280.4902      | -262.4876    | -2.6543         | -2.6728       |
+| 0.5233        | 0.88  | 1700 | 0.5206          | -0.4573        | -2.0951          | 0.7812             | 1.6377          | -277.9205      | -258.8084    | -2.6870         | -2.7097       |
+| 0.5593        | 0.93  | 1800 | 0.5231          | -0.5508        | -2.2000          | 0.7969             | 1.6492          | -278.9703      | -259.7433    | -2.6221         | -2.6519       |
+| 0.4967        | 0.98  | 1900 | 0.5290          | -0.5340        | -1.9570          | 0.8281             | 1.4230          | -276.5395      | -259.5749    | -2.6564         | -2.6878       |
+| 0.0921        | 1.03  | 2000 | 0.5368          | -1.1376        | -3.1615          | 0.7812             | 2.0239          | -288.5854      | -265.6111    | -2.6040         | -2.6345       |
+| 0.0733        | 1.08  | 2100 | 0.5453          | -1.1045        | -3.4451          | 0.7656             | 2.3406          | -291.4208      | -265.2799    | -2.6289         | -2.6595       |
+| 0.0972        | 1.14  | 2200 | 0.5571          | -1.6915        | -3.9823          | 0.8125             | 2.2908          | -296.7934      | -271.1505    | -2.6471         | -2.6709       |
+| 0.1058        | 1.19  | 2300 | 0.5789          | -1.0621        | -3.8941          | 0.7969             | 2.8319          | -295.9106      | -264.8563    | -2.5527         | -2.5798       |
+| 0.2423        | 1.24  | 2400 | 0.5455          | -1.1963        | -3.5590          | 0.7812             | 2.3627          | -292.5599      | -266.1981    | -2.5414         | -2.5784       |
+| 0.1177        | 1.29  | 2500 | 0.5889          | -1.8141        | -4.3942          | 0.7969             | 2.5801          | -300.9120      | -272.3761    | -2.4802         | -2.5189       |
+| 0.1213        | 1.34  | 2600 | 0.5683          | -1.4608        | -3.8420          | 0.8125             | 2.3812          | -295.3901      | -268.8436    | -2.4774         | -2.5207       |
+| 0.0889        | 1.39  | 2700 | 0.5890          | -1.6007        | -3.7337          | 0.7812             | 2.1330          | -294.3068      | -270.2423    | -2.4123         | -2.4522       |
+| 0.0995        | 1.45  | 2800 | 0.6073          | -1.5519        | -3.8362          | 0.8281             | 2.2843          | -295.3315      | -269.7538    | -2.4685         | -2.5050       |
+| 0.1145        | 1.5   | 2900 | 0.5790          | -1.7939        | -4.2876          | 0.8438             | 2.4937          | -299.8461      | -272.1744    | -2.4272         | -2.4674       |
+| 0.0644        | 1.55  | 3000 | 0.5735          | -1.7285        | -4.2051          | 0.8125             | 2.4766          | -299.0209      | -271.5201    | -2.4193         | -2.4574       |
+| 0.0798        | 1.6   | 3100 | 0.5537          | -1.7226        | -4.2850          | 0.8438             | 2.5624          | -299.8200      | -271.4610    | -2.5367         | -2.5696       |
+| 0.1013        | 1.65  | 3200 | 0.5575          | -1.5715        | -3.9813          | 0.875              | 2.4098          | -296.7825      | -269.9498    | -2.4926         | -2.5267       |
+| 0.1254        | 1.7   | 3300 | 0.5905          | -1.6412        | -4.4703          | 0.8594             | 2.8291          | -301.6730      | -270.6473    | -2.5017         | -2.5340       |
+| 0.085         | 1.76  | 3400 | 0.6133          | -1.9159        | -4.6760          | 0.8438             | 2.7601          | -303.7296      | -273.3941    | -2.4614         | -2.4960       |
+| 0.065         | 1.81  | 3500 | 0.6074          | -1.8237        | -4.3525          | 0.8594             | 2.5288          | -300.4951      | -272.4724    | -2.4597         | -2.5004       |
+| 0.0755        | 1.86  | 3600 | 0.5836          | -1.9252        | -4.4005          | 0.8125             | 2.4753          | -300.9748      | -273.4872    | -2.4327         | -2.4716       |
+| 0.0746        | 1.91  | 3700 | 0.5789          | -1.9280        | -4.4906          | 0.8125             | 2.5626          | -301.8762      | -273.5149    | -2.4686         | -2.5115       |
+| 0.1348        | 1.96  | 3800 | 0.6015          | -1.8658        | -4.2428          | 0.8281             | 2.3769          | -299.3976      | -272.8936    | -2.4943         | -2.5393       |
+| 0.0217        | 2.01  | 3900 | 0.6122          | -2.3335        | -4.9229          | 0.8281             | 2.5894          | -306.1988      | -277.5699    | -2.4841         | -2.5272       |
+| 0.0219        | 2.07  | 4000 | 0.6522          | -2.9890        | -6.0164          | 0.8281             | 3.0274          | -317.1334      | -284.1248    | -2.4105         | -2.4545       |
+| 0.0119        | 2.12  | 4100 | 0.6922          | -3.4777        | -6.6749          | 0.7969             | 3.1972          | -323.7187      | -289.0121    | -2.4272         | -2.4699       |
+| 0.0153        | 2.17  | 4200 | 0.6993          | -3.2406        | -6.6775          | 0.7969             | 3.4369          | -323.7453      | -286.6413    | -2.4047         | -2.4465       |
+| 0.011         | 2.22  | 4300 | 0.7178          | -3.7991        | -7.4397          | 0.7656             | 3.6406          | -331.3667      | -292.2260    | -2.3843         | -2.4290       |
+| 0.0072        | 2.27  | 4400 | 0.6840          | -3.3269        | -6.8021          | 0.8125             | 3.4752          | -324.9908      | -287.5042    | -2.4095         | -2.4536       |
+| 0.0197        | 2.32  | 4500 | 0.7013          | -3.6890        | -7.3014          | 0.8125             | 3.6124          | -329.9841      | -291.1250    | -2.4118         | -2.4543       |
+| 0.0182        | 2.37  | 4600 | 0.7476          | -3.8994        | -7.5366          | 0.8281             | 3.6372          | -332.3356      | -293.2291    | -2.4163         | -2.4565       |
+| 0.0125        | 2.43  | 4700 | 0.7199          | -4.0560        | -7.5765          | 0.8438             | 3.5204          | -332.7345      | -294.7952    | -2.3699         | -2.4100       |
+| 0.0082        | 2.48  | 4800 | 0.7048          | -3.6613        | -7.1356          | 0.875              | 3.4743          | -328.3255      | -290.8477    | -2.3925         | -2.4303       |
+| 0.0118        | 2.53  | 4900 | 0.6976          | -3.7908        | -7.3152          | 0.8125             | 3.5244          | -330.1224      | -292.1431    | -2.3633         | -2.4047       |
+| 0.0118        | 2.58  | 5000 | 0.7198          | -3.9049        | -7.5557          | 0.8281             | 3.6508          | -332.5271      | -293.2844    | -2.3764         | -2.4194       |
+| 0.006         | 2.63  | 5100 | 0.7506          | -4.2118        | -7.9149          | 0.8125             | 3.7032          | -336.1194      | -296.3530    | -2.3407         | -2.3860       |
+| 0.0143        | 2.68  | 5200 | 0.7408          | -4.2433        | -7.9802          | 0.8125             | 3.7369          | -336.7721      | -296.6682    | -2.3509         | -2.3946       |
+| 0.0057        | 2.74  | 5300 | 0.7552          | -4.3392        | -8.0831          | 0.7969             | 3.7439          | -337.8013      | -297.6275    | -2.3388         | -2.3842       |
+| 0.0138        | 2.79  | 5400 | 0.7404          | -4.2395        | -7.9762          | 0.8125             | 3.7367          | -336.7322      | -296.6304    | -2.3286         | -2.3737       |
+| 0.0079        | 2.84  | 5500 | 0.7525          | -4.4466        | -8.2196          | 0.7812             | 3.7731          | -339.1662      | -298.7007    | -2.3200         | -2.3641       |
+| 0.0077        | 2.89  | 5600 | 0.7520          | -4.5586        | -8.3485          | 0.7969             | 3.7899          | -340.4545      | -299.8206    | -2.3078         | -2.3517       |
+| 0.0094        | 2.94  | 5700 | 0.7527          | -4.5542        | -8.3509          | 0.7812             | 3.7967          | -340.4790      | -299.7773    | -2.3062         | -2.3510       |
+| 0.0054        | 2.99  | 5800 | 0.7520          | -4.5169        | -8.3079          | 0.7812             | 3.7911          | -340.0493      | -299.4038    | -2.3081         | -2.3530       |
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.12.0
+- Tokenizers 0.14.0
+
+## Citation
+
+If you find Zephyr-7B-β is useful in your work, please cite it with:
+
+```
+@misc{tunstall2023zephyr,
+      title={Zephyr: Direct Distillation of LM Alignment}, 
+      author={Lewis Tunstall and Edward Beeching and Nathan Lambert and Nazneen Rajani and Kashif Rasul and Younes Belkada and Shengyi Huang and Leandro von Werra and Clémentine Fourrier and Nathan Habib and Nathan Sarrazin and Omar Sanseviero and Alexander M. Rush and Thomas Wolf},
+      year={2023},
+      eprint={2310.16944},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_HuggingFaceH4__zephyr-7b-beta)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 52.15   |
+| ARC (25-shot)         | 62.03          |
+| HellaSwag (10-shot)   | 84.36    |
+| MMLU (5-shot)         | 61.07         |
+| TruthfulQA (0-shot)   | 57.45   |
+| Winogrande (5-shot)   | 77.74   |
+| GSM8K (5-shot)        | 12.74        |
+| DROP (3-shot)         | 9.66         |

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

mlc-chat-config.json

@@ -0,0 +1,23 @@
+{
+    "model_lib": "zephyr-7b-beta-chatRDM-q4f32_1",
+    "local_id": "zephyr-7b-beta-q4f32_1",
+    "conv_template": "mistral_default",
+    "temperature": 0.7,
+    "repetition_penalty": 1.0,
+    "top_p": 0.95,
+    "mean_gen_len": 128,
+    "max_gen_len": 16384,
+    "num_shards": 1,
+    "use_presharded_weights": false,
+    "shift_fill_factor": 0.3,
+    "tokenizer_files": [
+        "tokenizer.json",
+        "added_tokens.json",
+        "tokenizer.model"
+    ],
+    "model_category": "mistral",
+    "model_name": "zephyr-7b-beta",
+    "vocab_size": 32000,
+    "prefill_chunk_size": 4096,
+    "sliding_window": 4096
+}

mod_cache_before_build.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d472420ec1330370bdb12a10bed0cbcbc71b39365836e7598b76cef21418b082
+size 32041362

params_shard_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c67aba48951be930fcafcd0fb3fe3656bbd9e9a3dd0ecfd8962bf53a58ae7d
+size 65536000

params_shard_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c31437f948f7020611065ab398fccff1108cbcfcdabc37bcdf920a660ed5500
+size 32112640

params_shard_10.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21c06f44bfafa74ac26103e93afb1498effd97db89b2fb6d6bbb8131645d4b7
+size 26214400

params_shard_100.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36ce1115de518e23a13b0f9f7c09b34f1e45d452426e3647922d59fbadf5143
+size 22052864

params_shard_101.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631a1e1ce577b3cb72f451b18bf018f6ea63a3437974bf1f15e2083e50969866
+size 58720256

params_shard_102.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e567a24bd7e68c283bf306724e87045c96658bc638baf3e8dc9a9f9112250f4
+size 26214400

params_shard_103.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa512cc3c9f8cb8fd8ecf9c58ec9057a956a2db83ae92de64e1f27fd25536fdc
+size 29360128

params_shard_104.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389900dafd761a1076ecc51a837ea9d39c8248d9e0f84a2805f5539fff3fe690
+size 22052864

params_shard_105.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a928c53c4126d78e9d3d462d655d40060fcd227d61ea72510e66a74a0275b749
+size 58720256

params_shard_106.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96211089d0f95e3ae21ac52a63b4e7aef3c39274586961641894e4c9ceebe16f
+size 26214400

params_shard_107.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45f3300f64d14265389785ed9f8b2f17333da4a770ddae69265ac1e6c67d466
+size 29360128

params_shard_108.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b5727046107dc9d94e56845cd0d3ec42ab2f1931967af0cf82ddaf87f101c8
+size 22052864

params_shard_109.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e309ade3afd20ac29d3df51a0a7fbca7494d7d6c12b2f4ac8758b8c7d39607
+size 58720256

params_shard_11.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b08a683623ecc850564a0745c441506adb52576404fec52e43ef9c2cc46f922b
+size 29360128

params_shard_110.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf1ca7fdad52ae4e10d8305dce7071582a1b9192d1872b19ba0aabedf93dbdd
+size 26214400

params_shard_111.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e230675c03fe3776708944e5e01926ca4446a37b483455cce5700f23b461c5
+size 29360128

params_shard_112.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b07a17697fd00280783e9a2e7a6babc47754a20e72dbd37a166355cace48626
+size 22052864

params_shard_113.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f2dfb287bf2628e24f86794b6287262dad651e211bdb63d09db010bcb65b4a
+size 58720256

params_shard_114.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:805f1952ceacc776758b6025e4ca6a414ea325a220399d0024839b6556e79576
+size 26214400

params_shard_115.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060dfc9380835d89aeada0a9fc04de1d42c4f611d82f7db5222d1dda7c9c333b
+size 29360128

params_shard_116.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515cabce85f08ed1df13a1d36ff79a12e0749037b35643556cf205ceb921ef03
+size 22052864

params_shard_117.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac694299b6ae19b4f65aaef44cbb6b170acb539aa511663aff081ef5a85aea83
+size 58720256

params_shard_118.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0faad8c321835deb1a3a1fb286bf0d8f2b219d305e8a5e48bf718bacc1568c
+size 26214400

params_shard_119.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d46224cfca64dc0de596ce47e363e7d2ac70b47120d92579b55473fa11acf94
+size 29360128

params_shard_12.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161918f0364169c97e1f3efce60988fabc7a69170dac25f38be583dc8a54a779
+size 22052864

params_shard_120.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12712b71b9229d2a7cd520d63c1a4b6875304669c648cefe829aab8c5b19a663
+size 22052864

params_shard_121.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f199431ed2419eef39c52c00b2bea1f70101199ff22448485e8d0496c0c2be2
+size 58720256

params_shard_122.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d32a150ce3449c4357bebc76f8966e414feca8d39e09879bbbf1f548a53990
+size 26214400

params_shard_123.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c6856de69668883cd473282f4df18bbaa0b8209b22e505f01f9995b0de6238b
+size 29360128

params_shard_124.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55262fec8a7580e58e683d707dd3a77ae71eaf7e5c91a11db6965861d1845b18
+size 22052864

params_shard_125.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6b0b7b635b319cd1ad7ab2027323a1cf4476a3bd5b7cc4e379e9d3a8ff1453
+size 58720256

params_shard_126.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc068decb257b57a7dee18dcfee6e13c792720b13757b4a3108419f0c6e936c5
+size 26214400

params_shard_127.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25b38aea0caf52dbcf416eff72d2e2e97b6b0b87718e419fb5aa7b8f4739f55
+size 29360128

params_shard_128.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344677f90a779cda44797cfbbf2541ab682d43e8e520c9156c1fa8e07b3ab84f
+size 65536000

params_shard_129.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a31315a1ecf8ae2157b77912218aca44749b5513c45022c01d70ca6f350a5b0
+size 22069248

params_shard_13.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745afbc415c6633cf34f152e4f88a19f0adc6af1fdf0acc56836afac39b397db
+size 58720256

params_shard_130.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7c5d00723beeb5ca5b38404de413cc8d3711ec8439be77130a8afad0689f03
+size 18481152

params_shard_14.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5574e7d49778d028bf3bebf3553e95ff7c1df4058ad99d5093e1b5a623b40b
+size 26214400

params_shard_15.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a24b4e96252ae86dc66d8f0cae44dae0fe8d430c96e4d92d5f0de9bc2b0905d
+size 29360128

params_shard_16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51287a06d5d0c20c6d99b0303864ba19de24d4ef54f5c9db82b767ec967a38f4
+size 22052864

params_shard_17.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89df4df2dbe4a6cf2fbeb70a712e65fcd58fa29afae07d6cd5e3bec7ce6807f8
+size 58720256

params_shard_18.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb5c1ba2d1174ea16bf1c38d9e1351b70e7376bdff177a55f8b4a37f2b01cc75
+size 26214400

params_shard_19.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea0941e14a04d4ec941fd768d17ca2742dea87c7c93c1b1e2a976d07f4b6ed9
+size 29360128

params_shard_2.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:623329f9bebb12d686883795fab9cd211d8df646d687a946070a78784f9e2e27
+size 58720256

params_shard_20.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082be09805aafc602dc56652d8bcfc8741afa3833a1c28e834e80d357534d5c4
+size 22052864