1bit Autotrain compatible Base model:cognitivecomputatio... Base model:finetune:cognitivec... Conversational Endpoints compatible Mistral Pruna-ai Quantized Region:us
Model Card on HF 🤗: https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2.9.2-Phi-3-Medium-HQQ-1bit-smashed
Cognitivecomputations Dolphin 2.9.2 Phi 3 Medium HQQ 1bit Smashed Benchmarks
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)
Cognitivecomputations Dolphin 2.9.2 Phi 3 Medium HQQ 1bit Smashed Parameters and Internals
| Additional Notes |
|
| LLM Name | Cognitivecomputations Dolphin 2.9.2 Phi 3 Medium HQQ 1bit Smashed |
| Repository 🤗 | https://huggingface.co/PrunaAI/cognitivecomputations-dolphin-2.9.2-Phi-3-Medium-HQQ-1bit-smashed |
| Base Model(s) | |
| Required VRAM | 2.7 GB |
| Updated | 2025-01-15 |
| Maintainer | PrunaAI |
| Model Type | mistral |
| Model Files | |
| Quantization Type | 1bit |
| Model Architecture | MistralForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.40.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|placeholder6|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to Cognitivecomputations Dolphin 2.9.2 Phi 3 Medium HQQ 1bit Smashed
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| NemoMix Unleashed EXL2 4bpw | 1000K / 7.3 GB | 54 | 6 |
| ...eZephir Sft Instruct Ead 16bit | 32K / 14.4 GB | 56 | 0 |
| ...cr To Json V1 HQQ 1bit Smashed | 32K / 1.6 GB | 20 | 0 |
| ...cr To Json V1 HQQ 4bit Smashed | 32K / 4.2 GB | 17 | 0 |
| ScikitLLM Model EXL2 | 32K / 3 GB | 4 | 1 |
| Chargen V2 8bpw EXL2 | 32K / 7.4 GB | 7 | 1 |
| ...tral PairRM DPO 8.0bpw H8 EXL2 | 32K / 7.4 GB | 8 | 2 |
| HamSter 0.2 8.0bpw H8 EXL2 | 32K / 7.4 GB | 10 | 1 |
| ...N L1 Chat RL V1.6.0bpw H6 EXL2 | 32K / 5.6 GB | 13 | 1 |
| ...N L1 Chat RL V1.3.0bpw H6 EXL2 | 32K / 3 GB | 11 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/cognitivecomputations-dolphin-2.9.2-Phi-3-Medium-HQQ-1bit-smashed .
Rank the Cognitivecomputations Dolphin 2.9.2 Phi 3 Medium HQQ 1bit Smashed 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? 41418 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227