Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,23 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+imat-bf16-gmerged.dat filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+sfr-iterative-dpo-llama-3-8b-r-imat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,143 @@
+---
+license: cc-by-nc-nd-3.0
+pipeline_tag: text-generation
+base_model: Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R
+tags:
+- salesforce
+- llama
+- llama-3
+- instruct
+- finetune
+- gguf
+- imatrix
+- importance matrix
+model-index:
+- name: SFR-Iterative-DPO-LLaMA-3-8B-R-iMat-GGUF
+  results: []
+---
+
+# Quant Infos
+
+- quants done with an importance matrix for improved quantization loss
+- gguf & imatrix generated from bf16 for "optimal" accuracy loss
+- Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S
+- Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) commit [dc685be46622a8fabfd57cfa804237c8f15679b8](https://github.com/ggerganov/llama.cpp/commit/dc685be46622a8fabfd57cfa804237c8f15679b8) (master as of 2024-05-12)
+- Imatrix generated with [this](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) multi-purpose dataset.
+  ```
+  ./imatrix -c 512 -m $model_name-f16.gguf -f $llama_cpp_path/groups_merged.txt -o $out_path/imat-f16-gmerged.dat
+  ```
+
+# Original Model Card:
+
+
+# SFR-Iterative-DPO-Llama-3-8B-R
+
+## Introduction
+We release a state-of-the-art instruct model of its class, **SFR-Iterative-DPO-LLaMA-3-8B-R**.
+On all three widely-used instruct model benchmarks: **Alpaca-Eval-V2**, **MT-Bench**, **Chat-Arena-Hard**, our model outperforms all models of similar size (e.g., LLaMA-3-8B-it), most large open-sourced models (e.g., Mixtral-8x7B-it),
+and strong proprietary models (e.g., GPT-3.5-turbo-0613). The model is trained with open-sourced datasets without any additional human-/GPT4-labeling.
+
+## Model Releases
+- [SFT model](https://huggingface.co/Salesforce/SFR-SFT-LLaMA-3-8B-R)
+- [Reward model](https://huggingface.co/Salesforce/SFR-RM-LLaMA-3-8B-R)
+- [RLHF model](https://huggingface.co/Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R)
+
+
+## Training methods
+We have developed a simple and efficient online RLHF recipe for LLM instruct training. Our recipe is DPO-based and thus much cheaper and simpler to train and tune compared to PPO-based approaches.
+Unlike widely-used offline DPO, the online component of our approach effectively mitigates distribution shifts during policy optimization.
+For a detailed exposition, please refer to our accompanying technical report.
+
+
+## Chat Benchmarks
+
+| **Model**               | **Size** | **Method**        | **LC Alpaca-Eval-V2** | **MT-Bench** | **Chat-Arena-Hard** |
+|-------------------------|----------|-------------------|-----------------------|--------------|---------------------|
+| **Small Open-Sourced Models**           |          |                   |                       |              |                     |
+| Gemma-7B-it             | 7B       | SFT               | 10.4                  | 6.38         | 7.5                 |
+| Zephyr-7B-beta          | 7B       | Vanilla DPO       | 13.1                  | 7.34         | -                   |
+| Mistral-7B-v0.2-it      | 7B       | SFT               | 17.1                  | 7.51         | 12.6                |
+| Open-Chat-0106          | 7B       | SFT               | 15.6                  | 7.8          | -                   |
+| Starling-7B-beta        | 7B       | PPO               | 25.8                  | 8.12         | 23.0                |
+| LLaMA-3-8B-it           | 8B       | RS+DPO+PPO        | 22.9                  | 8.16         | 20.6                |
+| **Ours**                |          |                   |                       |              |                     |
+| Ours (SFT baseline)     | 8B       | SFT               | 10.2                  | 7.69         | 5.6                 |
+| Ours (DPO baseline)     | 8B       | Vanilla DPO       | 22.5                  | 8.17         | 22.4                |
+| Ours (Online RLHF)      | 8B       | Iterative DPO     | **37.2**              | **8.46**     | **29.1**            |
+| **Large Open-Sourced Models**       |          |                   |                       |              |                     |
+| Vicuna-33b-v1.3         | 33B      | SFT               | 17.6                  | 7.12         | 8.6                 |
+| Yi-34B-Chat             | 34B      | SFT               | 27.2                  | -            | 23.1                |
+| Mixtral-8x7B-it         | 45B*     | SFT               | 23.7                  | 8.30         | 23.4                |
+| Tulu-2-DPO-70B          | 70B      | Vanilla DPO       | 21.2                  | 7.89         | 15.0                |
+| LLaMA-3-70B-it          | 70B      | RS+DPO+PPO        | 34.4                  | 8.95         | 41.1                |
+| Mixtral-8x22B-it        | 141B*    | SFT               | 30.9                  | 8.66         | 36.4                |
+| **Proprietary Models**  |       |                   |                       |              |                     |
+| GPT-3.5-turbo-1106      | -        | -                 | 19.3                  | 8.35         | 18.9                |
+| GPT-3.5-turbo-0613      | -        | -                 | 22.7                  | 8.39         | 24.8                |
+| GPT-4-0613              | -        | -                 | 30.2                  | 9.18         | 37.9                |
+| Claude-3-Opus           | -        | -                 | 40.5                  | 9.00         | 60.4                |
+| GPT-4 Turbo (04/09)     | -        | -                 | 55.0                  | -            | 82.6                |
+
+
+## Academic Benchmarks
+
+| **Model**                  | **Size** | **Method**      | **GSM-8K** | **MMLU** | **HumanEval** | **TruthfulQA** | **ARC** | **MBPP** |
+|----------------------------|----------|-----------------|------------|----------|---------------|----------------|---------|----------|
+| LLaMA-3-8B-it              | 8B       | RS+DPO+PPO      | 79.6       | 66.0     | 61.6          | 43.9           | 59.5    | 61.1     |
+| Ours (SFT baseline)        | 8B       | SFT             | 74.2       | 64.7     | 65.2          | 53.4           | 61.4    | 62.3     |
+| Ours (DPO baseline)        | 8B       | Vanilla DPO     | 79.8       | 64.5     | 63.4          | 61.8           | 65.2    | 60.3     |
+| Ours (Iterative RLHF)      | 8B       | Iterative DPO   | 80.7       | 65.3     | 64.6          | 60.4           | 64.3    | 60.8     |
+
+
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+device = "cuda" 
+
+model = AutoModelForCausalLM.from_pretrained("Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R")
+tokenizer = AutoTokenizer.from_pretrained("Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R")
+
+messages = [
+    {"role": "user", "content": "I'm trying to teach myself to have nicer handwriting. Can you help?"},
+]
+
+model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
+
+model_inputs = model_inputs.to(device)
+model.to(device)
+
+output_tokens = model.generate(model_inputs, max_new_tokens=1024, do_sample=True)
+model_outputs = tokenizer.batch_decode(output_tokens)
+print(model_outputs[0])
+```
+
+
+## Limitations
+SFR-Iterative-DPO-LLaMA-3-8B-R is a research model developed as part of our RLHF initiative at Salesforce. 
+While safety and ethical considerations are integral to our alignment process, 
+there remains the possibility that the model could generate offensive or unethical content, particularly under adversarial conditions. 
+We are committed to continuous improvement in our models to minimize such risks and encourage responsible usage.
+
+## Citation
+Please cite our papers if you find our models are useful.
+
+```bibtex
+@misc{dong2024rlhf,
+      title={RLHF Workflow: From Reward Modeling to Online RLHF}, 
+      author={Hanze Dong and Wei Xiong and Bo Pang and Haoxiang Wang and Han Zhao and Yingbo Zhou and Nan Jiang and Doyen Sahoo and Caiming Xiong and Tong Zhang},
+      year={2024},
+      eprint={2405.07863},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+
+@misc{xiong2024iterative,
+      title={Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint}, 
+      author={Wei Xiong and Hanze Dong and Chenlu Ye and Ziqi Wang and Han Zhong and Heng Ji and Nan Jiang and Tong Zhang},
+      year={2024},
+      eprint={2312.11456},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```

imat-bf16-gmerged.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee53f56f2874d69c49737c949b2f85d0ce5eba44576dae4037eb5ceecfc6f9cd
+size 4988185

sfr-iterative-dpo-llama-3-8b-r-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9662fac39ebb5cd1efc15758d2a1158beead31afc4de58fbbb8f9a2e6aa90339
+size 16068890912

sfr-iterative-dpo-llama-3-8b-r-imat-IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e90d03a961e7be9161af5a9e4b2252d53c3ee3d3f0f2c3fff600a358768142
+size 2019627616

sfr-iterative-dpo-llama-3-8b-r-imat-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23fdb43c8f18011fa2156a3711241e7a74d70c4d1913c7995a578f52b7242e76
+size 2948280928

sfr-iterative-dpo-llama-3-8b-r-imat-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0703b7a6fcd83badd3180052226b7ca8139c13c0563f6e2769918fd19763a492
+size 2758488672

sfr-iterative-dpo-llama-3-8b-r-imat-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700dcbc8b551af6d4e2638ec3eece08d10ad515d641e245a0606a3038ff7382a
+size 2605781600

sfr-iterative-dpo-llama-3-8b-r-imat-IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bdaac3b6f1b8401382dd667acb36c057360c0c18e1f13f4579aaf7aabdca7ad
+size 2399212128

sfr-iterative-dpo-llama-3-8b-r-imat-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d98e52a724f9ef2acd8688cc7825a5b776f789468be177bf808c9c12b5f04687
+size 3784823392

sfr-iterative-dpo-llama-3-8b-r-imat-IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd74ab4fa8673330c6abaa8386d530c1f25f5d695252d73d06de38ec4b57835
+size 3682325088

sfr-iterative-dpo-llama-3-8b-r-imat-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d08930c8b3cdc29c30f636f089b67739dda5c4bdb149333de4aa19fcc1afb5aa
+size 3518747232

sfr-iterative-dpo-llama-3-8b-r-imat-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:763c30bfe2c434917057c66f56ac51b9dbd5515e5b09ef445eea6f475af6702e
+size 3274912352

sfr-iterative-dpo-llama-3-8b-r-imat-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95ab77f9ab096ced6ff03525f9fc70087c90b5fb66d11bddc471b7cb2fc50df
+size 4677988960

sfr-iterative-dpo-llama-3-8b-r-imat-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d1a19f0ef23540e53356d4c1476194b433c53f798155bb2c27becb87139d6d
+size 4447662688

sfr-iterative-dpo-llama-3-8b-r-imat-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cc7b1459aa4a706752d3146e5d900e68d7af692960b7741abdb624985a9643d
+size 4675891808

sfr-iterative-dpo-llama-3-8b-r-imat-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3d68484fcfd893799e5f6776f4c7c6ef902fb3728f106dba468c9e5c61277b
+size 4920734304

sfr-iterative-dpo-llama-3-8b-r-imat-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0704dae075b19ef21d5d9ca870ab1e3a12e973aa71bbc05433aa464f7537320b
+size 4692669024

sfr-iterative-dpo-llama-3-8b-r-imat-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c2ae93d7b565aa96008986a419bf7c6456c1e31d92736f2961d7630420d90a9
+size 5732987488

sfr-iterative-dpo-llama-3-8b-r-imat-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e443649a761f1bcbb0eb50a8dfb93a09d32bcb099a102920f4f5b34aab7915
+size 5599294048

sfr-iterative-dpo-llama-3-8b-r-imat-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:393af1163456e7176163de61ed25bcba2a101be796bb0f31c9bdbf4c29bec421
+size 6596006496

sfr-iterative-dpo-llama-3-8b-r-imat-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61e322d34bf50ded57638458bd051424b5591fd51d5d7942e2b7bc90867646d6
+size 8540770912