4-bit Autotrain compatible Awq Base model:jondurbin/bagel-dpo... Conversational Dataset:ai2 arc Dataset:allenai/ultrafeedback ... Dataset:boolq Dataset:cais/mmlu Dataset:cakiki/rosetta-code Dataset:codeparrot/apps Dataset:datasets/winogrande Dataset:drop Dataset:facebook/belebele Dataset:intel/orca dpo pairs Dataset:jondurbin/airoboros-3.... Dataset:jondurbin/cinematika-v... Dataset:jondurbin/truthy-dpo-v... Dataset:julielab/emobank Dataset:kingbri/pippa-sharegpt Dataset:ldjnr/capybara Dataset:lmsys/lmsys-chat-1m Dataset:migtissera/synthia-v1.... Dataset:muennighoff/natural-in... Dataset:nvidia/helpsteer Dataset:open-orca/slimorca Dataset:openbookqa Dataset:piqa Dataset:spider Dataset:squad v2 Dataset:squish42/bluemoon-fand... Dataset:tiger-lab/mathinstruct Dataset:unalignment/toxic-dpo-... Dataset:vezora/tested-22k-pyth... License:apache-2.0 Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow
Bagel DPO 8x7b V0.2 AWQ Benchmarks
HF Avg Score: 63.6 vs 86.1 (GPT-4) -26.1%
ARC: 63.4-34.2%
HellaSwag: 72.6-23.8%
MMLU: 61.8-28.6%
TruthfulQA: 69.918.5%
WinoGrande: 81.6-6.7%
GSM8K: 36-60.9%
nn.n% — How the model compares to the GPT-4.
Rank the Bagel DPO 8x7b V0.2 AWQ Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
Best Alternatives to Bagel DPO 8x7b V0.2 AWQ
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| UNAversal 8x7B V1beta AWQ | 64.7 | 32K / 24.7 GB | 6 | 2 |
| Open Gpt4 8x7B V0.2 AWQ | 64.5 | 32K / 24.7 GB | 6 | 2 |
| ...ixtral Instruct 8x7b Zloss AWQ | 64.2 | 32K / 24.7 GB | 10 | 1 |
| ... Hermes 2 Mixtral 8x7B DPO AWQ | 64.1 | 32K / 24.7 GB | 433 | 20 |
| ...Hermes 2 Mixtral 8x7B DPO GPTQ | 64.1 | 32K / 24.7 GB | 1 | 1 |
| Notux 8x7b V1 AWQ | 64 | 32K / 24.7 GB | 6 | 3 |
| ...utLM Mixtral 8x7B Instruct AWQ | 63.8 | 32K / 24.7 GB | 468 | 2 |
| Mixtral 8x7B Instruct V0.1 AWQ | 63.7 | 32K / 24.7 GB | 1025 | 54 |
| ...Mixtral 8x7B V0.1 Dolly15K AWQ | 63.5 | 32K / 24.7 GB | 6 | 1 |
| ... Hermes 2 Mixtral 8x7B SFT AWQ | 63.2 | 32K / 24.7 GB | 48 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/bagel-dpo-8x7b-v0.2-AWQ .
Bagel DPO 8x7b V0.2 AWQ Parameters and Internals
| LLM Name | Bagel DPO 8x7b V0.2 AWQ |
| Repository | Open on 🤗 |
| Model Name | Bagel DPO 8X7B V0.2 |
| Model Creator | Jon Durbin |
| Base Model(s) | |
| Model Size | 6.5b |
| Required VRAM | 24.7 GB |
| Updated | 2024-07-01 |
| Maintainer | TheBloke |
| Model Type | mixtral |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Initializer Range | 0.02 |
| Torch Data Type | float16 |
What open-source LLMs or SLMs are you in search of? 34238 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801