8-bit Autotrain compatible Codegen Conversational Endpoints compatible Instruct Llama Region:us Safetensors Sharded Tensorflow
Deepseek Coder 6.7B Instruct Trt Int8 G128 Hf 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)
Deepseek Coder 6.7B Instruct Trt Int8 G128 Hf Parameters and Internals
| LLM Name | Deepseek Coder 6.7B Instruct Trt Int8 G128 Hf |
| Repository 🤗 | https://huggingface.co/juewang/deepseek-coder-6.7b-instruct-trt-int8-g128-hf |
| Model Size | 6.7b |
| Required VRAM | 7.2 GB |
| Updated | 2024-10-18 |
| Maintainer | juewang |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.41.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 32256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Deepseek Coder 6.7B Instruct Trt Int8 G128 Hf
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Speechless Coder Ds 6.7B | 16K / 13.5 GB | 1125 | 5 |
| Code 290K 6.7B Instruct | 16K / 13.5 GB | 71 | 6 |
| Datascience Coder 6.7B | 16K / 13.5 GB | 1006 | 3 |
| Merge Code Gen | 16K / 13.6 GB | 6 | 0 |
| Hpc Coder V2.6.7B | 16K / 27.1 GB | 54 | 4 |
| ... 6.7B Instruct Trt Int4 G64 Hf | 16K / 4.2 GB | 5 | 0 |
| NaturalSQL 6.7B V0 | 16K / 13.5 GB | 593 | 6 |
| SQL Sorcerer 6.7B V1.1 | 16K / 13.5 GB | 7 | 0 |
| DeepYi Second | 16K / 12.6 GB | 5 | 0 |
| SQL Sorcerer 6.7B V1.0 | 16K / 13.5 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than juewang/deepseek-coder-6.7b-instruct-trt-int8-g128-hf .
Rank the Deepseek Coder 6.7B Instruct Trt Int8 G128 Hf 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803