Merged Model 4-bit Autotrain compatible Awq Base model:ehartford/dolphin-2... Base model:quantized:ehartford... Dataset:ehartford/dolphin Dataset:ehartford/samantha-dat... Dataset:ehartford/wizardlm evo... Dataset:jondurbin/airoboros-2.... En Instruct Llama Quantized Region:us Safetensors Sharded Tensorflow
Dolphin 2.2 70B AWQ Parameters and Internals
| LLM Name | Dolphin 2.2 70B AWQ |
| Repository | Open on 🤗 |
| Model Name | Dolphin 2.2 70B |
| Model Creator | Eric Hartford |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 70b |
| Required VRAM | 36.6 GB |
| Updated | 2024-07-27 |
| Maintainer | TheBloke |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | LlamaForCausalLM |
| License | llama2 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.34.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32002 |
| Torch Data Type | float16 |
Best Alternatives to Dolphin 2.2 70B AWQ
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ...0B Instruct Gradient 1048K AWQ | 0.2 | 1024K / 39.9 GB | 73 | 1 |
| ...70B Instruct Gradient 262K AWQ | 0.3 | 256K / 39.9 GB | 368 | 0 |
| Llama 3 70B Instruct AWQ | 0.3 | 8K / 39.9 GB | 142536 | 64 |
| Llama 3 70B Instruct AWQ | 0.3 | 8K / 39.9 GB | 3492 | 1 |
| Meta Llama 3 70B Instruct AWQ | 0.3 | 8K / 39.9 GB | 1515 | 10 |
| Llama 3 128K 70B Instruct AWQ | 0.3 | 8K / 39.9 GB | 176 | 0 |
| ... SauerkrautLM 70B Instruct AWQ | 0.3 | 8K / 39.9 GB | 190 | 0 |
| Llama 3 70B Instruct AWQ | 0.2 | 8K / 39.9 GB | 81 | 1 |
| ...Typhoon V1.5x 70B Instruct AWQ | 0.2 | 8K / 39.9 GB | 98 | 1 |
| Meta Llama 3 70B Instruct AWQ | 0.2 | 8K / 39.9 GB | 12 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/dolphin-2.2-70B-AWQ .
Rank the Dolphin 2.2 70B AWQ 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501