4-bit Autotrain compatible Base model:jondurbin/nontoxic-... 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/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/spicy-3.1 Dataset:unalignment/toxic-dpo-... Dataset:vezora/tested-22k-pyth... Gptq License:other Llama Quantized Region:us Safetensors
Nontoxic Bagel 34B V0.2 GPTQ Benchmarks
HF Avg Score: 65.5 vs 86.1 (GPT-4) -23.9%
ARC: 63.7-33.9%
HellaSwag: 71.9-24.6%
MMLU: 67.2-22.3%
TruthfulQA: 69.818.3%
WinoGrande: 80.8-7.7%
GSM8K: 42.1-54.2%
nn.n% — How the model compares to the GPT-4.
Rank the Nontoxic Bagel 34B V0.2 GPTQ 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 Nontoxic Bagel 34B V0.2 GPTQ
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| SUS Chat 34B | 85.03 | 8K / 68.9 GB | 2632 | 118 |
| SUS Chat 34B GPTQ | 74.6 | 8K / 18.6 GB | 6 | 3 |
| SUS Chat 34B AWQ | 74.6 | 8K / 19.3 GB | 55 | 9 |
| Tess 34B V1.5B | 70.31 | 195K / 69.2 GB | 1610 | 14 |
| Tess M V1.3 | 69.71 | 195K / 69.2 GB | 4086 | 25 |
| Yi 34B | 69.42 | 4K / 68.9 GB | 11959 | 1264 |
| Blossom V3.1 Yi 34B | 68.16 | 4K / 68.9 GB | 2509 | 7 |
| PlatYi 34B 200K Q FastChat | 67.85 | 195K / 68.9 GB | 2285 | 3 |
| Yi 1.5 34B Chat GGUF | 65.6 | 4K / 8.9 GB | 729 | 4 |
| Nontoxic Bagel 34B V0.2 AWQ | 65.5 | 195K / 19.3 GB | 6 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/nontoxic-bagel-34b-v0.2-GPTQ .
Nontoxic Bagel 34B V0.2 GPTQ Parameters and Internals
| LLM Name | Nontoxic Bagel 34B V0.2 GPTQ |
| Repository | Open on 🤗 |
| Model Name | Nontoxic Bagel 34B v0.2 |
| Model Creator | Jon Durbin |
| Base Model(s) | |
| Model Size | 34b |
| Required VRAM | 18.6 GB |
| Updated | 2024-06-24 |
| Maintainer | TheBloke |
| Model Type | llama |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 200000 |
| Model Max Length | 200000 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 64000 |
| Initializer Range | 0.02 |
| Torch Data Type | bfloat16 |
What open-source LLMs or SLMs are you in search of? 34902 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801