Merged Model Autotrain compatible Base model:jondurbin/bagel-dpo... Base model:nousresearch/nous-h... Conversational Endpoints compatible Jondurbin/bagel-dpo-34b-v0.2 Llama Model-index Nousresearch/nous-hermes-2-yi-... Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/dfurman/HermesBagel-34B-v0.1
HermesBagel 34B V0.1 Benchmarks
ARC: 70.56 vs 96.7 (so35)-27%
HellaSwag: 85.74 vs 95.3 (gpt4)-10%
MMLU: 77.38 vs 88.3 (so35)-12.4%
TruthfulQA: 67.34 vs 59 (gpt4)14.1%
WinoGrande: 84.61 vs 87.5 (gpt4)-3.3%
GSM8K: 65.28 vs 96.4 (so35)-32.3%
LLME Score: 0.17604
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
HermesBagel 34B V0.1 Parameters and Internals
| Model Type |
| |
| Additional Notes |
|
| LLM Name | HermesBagel 34B V0.1 |
| Repository 🤗 | https://huggingface.co/dfurman/HermesBagel-34B-v0.1 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 34b |
| Required VRAM | 68.9 GB |
| Updated | 2024-12-21 |
| Maintainer | dfurman |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 64000 |
| Torch Data Type | bfloat16 |
Best Alternatives to HermesBagel 34B V0.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Casual Magnum 34B | 195K / 68.8 GB | 13 | 1 |
| 34B Beta | 195K / 69.2 GB | 3548 | 62 |
| Yi 34B 200K | 195K / 68.9 GB | 4525 | 317 |
| Smaug 34B V0.1 | 195K / 69.2 GB | 3718 | 60 |
| Bagel Hermes 34B Slerp | 195K / 68.9 GB | 3986 | 1 |
| Bagel 34B V0.2 | 195K / 68.7 GB | 3954 | 39 |
| Yi 34B 200K AEZAKMI V2 | 195K / 69.2 GB | 1210 | 12 |
| Smaug 34B V0.1 ExPO | 195K / 69.2 GB | 2966 | 0 |
| Faro Yi 34B | 195K / 69.2 GB | 3749 | 6 |
| Bagel DPO 34B V0.5 | 195K / 68.7 GB | 3008 | 17 |
Note: green Score (e.g. "73.2") means that the model is better than dfurman/HermesBagel-34B-v0.1 .
Rank the HermesBagel 34B V0.1 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! 🌟
What open-source LLMs or SLMs are you in search of? 40013 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217