---
title: salamandra-7b-instruct-mlx-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/salamandra-7b-instruct-mlx-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/salamandra-7b-instruct-mlx-bf16.md"
repository: mlx-community/salamandra-7b-instruct-mlx-bf16
last_updated: 2025-08-21
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
base_model:
  - BSC-LT/salamandra-7b-instruct
base_model_relation: finetune
parameters: 7.8B
tensor_type:
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - bg
  - ca
  - code
  - cs
  - cy
  - da
  - de
  - el
  - en
  - es
  - et
  - eu
  - fi
  - fr
  - ga
  - gl
  - hr
  - hu
  - it
  - lt
  - lv
  - mt
  - nl
  - nn
  - "\\no"
  - oc
  - pl
  - pt
  - ro
  - ru
  - sh
  - sk
  - sl
  - sr
  - sv
  - uk
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 93
stars: 0
tags:
  - mlx
---

# salamandra-7b-instruct-mlx-bf16

> salamandra-7b-instruct-mlx-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/salamandra-7b-instruct-mlx-bf16

mlx-community/salamandra-7b-instruct-mlx-bf16 是 ModelScope 魔搭社区上的 7.8B 参数text-generation模型，采用 apache-2.0 许可，基于 BSC-LT/salamandra-7b-instruct 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/salamandra-7b-instruct-mlx-bf16
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 7.8B
- **Base model**: BSC-LT/salamandra-7b-instruct
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 93
- **Stars**: 0
- **Last updated**: 2025-08-21

Source: https://www.modelscope.cn/models/mlx-community/salamandra-7b-instruct-mlx-bf16

---

# mlx-community/salamandra-7b-instruct-mlx-bf16

The Model [mlx-community/salamandra-7b-instruct-mlx-bf16](https://huggingface.co/mlx-community/salamandra-7b-instruct-mlx-bf16) was converted to MLX format from [BSC-LT/salamandra-7b-instruct](https://huggingface.co/BSC-LT/salamandra-7b-instruct) using mlx-lm version **0.22.3**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("bibproj/salamandra-7b-instruct-mlx-fp16")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```