4-bit 4bit Autotrain compatible Awq Conversational Endpoints compatible Llama Quantized Region:us Safetensors Sharded Tensorflow
Saiga Llama3 70b Sft M1 D5 Abliterated AWQ 4bit 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)
Saiga Llama3 70B Sft M1 D5 Abliterated AWQ 4bit Parameters and Internals
| LLM Name | Saiga Llama3 70b Sft M1 D5 Abliterated AWQ 4bit |
| Repository 🤗 | https://huggingface.co/IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit |
| Base Model(s) | |
| Model Size | 70b |
| Required VRAM | 39.9 GB |
| Updated | 2024-09-16 |
| Maintainer | IlyaGusev |
| Model Type | llama |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq|4bit |
| Model Architecture | LlamaForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|begin_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | float16 |
Best Alternatives to Saiga Llama3 70B Sft M1 D5 Abliterated AWQ 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...0B Instruct Gradient 1048K AWQ | 1024K / 39.9 GB | 1 | 1 |
| ...70B Instruct Gradient 262K AWQ | 256K / 39.9 GB | 6 | 0 |
| MultiVerse 70B AWQ | 32K / 41.3 GB | 59 | 2 |
| Opus V1.2 70B AWQ | 32K / 36.7 GB | 13 | 1 |
| QuartetAnemoi 70B T0.0001 AWQ | 31K / 36.7 GB | 22 | 1 |
| Senku 70B AWQ 4bit GEMM | 31K / 36.7 GB | 16 | 1 |
| Kiqu 70B AWQ | 31K / 36.7 GB | 25 | 1 |
| CodeLlama 70B Hf AWQ | 16K / 36.6 GB | 25 | 4 |
| Llama 3 70B Instruct AWQ | 8K / 39.9 GB | 50365 | 66 |
| Dolphin 2.9.1 Llama 3 70B AWQ | 8K / 39.9 GB | 934 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_awq_4bit .
Rank the Saiga Llama3 70B Sft M1 D5 Abliterated AWQ 4bit 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? 35926 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803