4bit Autotrain compatible Conversational Dataset:ambrosfitz/10k history... Endpoints compatible Instruct Mistral Phi3 Pytorch Quantized Region:us Sft Sharded Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/ambrosfitz/phi3_history_v2
Phi3 History V2 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)
Phi3 History V2 Parameters and Internals
| LLM Name | Phi3 History V2 |
| Repository 🤗 | https://huggingface.co/ambrosfitz/phi3_history_v2 |
| Required VRAM | 7.6 GB |
| Updated | 2024-12-22 |
| Maintainer | ambrosfitz |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|placeholder6|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to Phi3 History V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...eZephir Sft Instruct Ead 16bit | 32K / 14.4 GB | 54 | 0 |
| ... Instruct Unsloth Merged 16bit | 4K / 7.6 GB | 38 | 1 |
| ... Mini 4K Instruct Bnb 4bit Ita | 4K / 7.6 GB | 2714 | 0 |
| Phired | 4K / 7.6 GB | 12 | 0 |
| ...ini New Model With Lora Merged | 4K / 7.6 GB | 5 | 0 |
| Phi 3 Mini Hospital Topic 50 | 4K / 7.6 GB | 19 | 0 |
| Model | 4K / 7.6 GB | 5 | 0 |
| MainPHI3 | 4K / 7.6 GB | 7 | 0 |
| Model | 4K / 7.6 GB | 9 | 0 |
| Phi3 Finetune Test | 4K / 7.6 GB | 17 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ambrosfitz/phi3_history_v2 .
Rank the Phi3 History V2 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217