4-bit Autotrain compatible Awq Endpoints compatible Mistral Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/luv2261/Codestral-22B-v0.1-hf-AWQ
Codestral 22B V0.1 Hf AWQ 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)
Codestral 22B V0.1 Hf AWQ Parameters and Internals
| LLM Name | Codestral 22B V0.1 Hf AWQ |
| Repository 🤗 | https://huggingface.co/luv2261/Codestral-22B-v0.1-hf-AWQ |
| Base Model(s) | |
| Model Size | 22b |
| Required VRAM | 12.2 GB |
| Updated | 2025-01-15 |
| Maintainer | luv2261 |
| Model Type | mistral |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | MistralForCausalLM |
| License | MNPL-0.1 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32768 |
| Torch Data Type | float16 |
Best Alternatives to Codestral 22B V0.1 Hf AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistral 22B V0.2 AWQ | 64K / 12.2 GB | 18 | 2 |
| Mistral 22B V0.1 AWQ | 64K / 12.2 GB | 21 | 1 |
| Codestral 22B V0.1 AWQ | 32K / 12.2 GB | 380 | 0 |
| Codestral 22B V0.1 Hf AWQ | 32K / 12.2 GB | 270 | 2 |
| Codestral 22B V0.1 AWQ | 32K / 12.2 GB | 31 | 0 |
| ... Instruct 0.2 Chkpt 200 16 Bit | 128K / 44.7 GB | 274 | 0 |
| MwM 22B Instruct | 128K / 44.7 GB | 28 | 0 |
| ...l 22B V0.1 Hf FIM Fix Bnb 4bit | 32K / 13.1 GB | 19 | 1 |
| Text2cypher Codestral 16bit | 32K / 44.7 GB | 33 | 3 |
| ... Abliterated V3.8.0bpw H8 EXL2 | 32K / 21.2 GB | 17 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than luv2261/Codestral-22B-v0.1-hf-AWQ .
Rank the Codestral 22B V0.1 Hf 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? 41362 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227