Instructions to use cs-552-2026-baseline/multilingual_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-baseline/multilingual_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-baseline/multilingual_model") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cs-552-2026-baseline/multilingual_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-baseline/multilingual_model") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use cs-552-2026-baseline/multilingual_model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cs-552-2026-baseline/multilingual_model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cs-552-2026-baseline/multilingual_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-baseline/multilingual_model
- SGLang
How to use cs-552-2026-baseline/multilingual_model with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "cs-552-2026-baseline/multilingual_model" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cs-552-2026-baseline/multilingual_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "cs-552-2026-baseline/multilingual_model" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cs-552-2026-baseline/multilingual_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-baseline/multilingual_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-baseline/multilingual_model
Automated MNLP evaluation report (2026-06-01)
#1
by zechen-nlp - opened
- EVAL_REPORT.md +138 -0
EVAL_REPORT.md
ADDED
|
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Automated MNLP evaluation report
|
| 2 |
+
|
| 3 |
+
- **Model repo:** [`cs-552-2026-baseline/multilingual_model`](https://huggingface.co/cs-552-2026-baseline/multilingual_model)
|
| 4 |
+
- **Owner(s):** group **baseline**
|
| 5 |
+
- **Generated at:** 2026-06-01T06:13:57+00:00 (UTC)
|
| 6 |
+
- **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci)
|
| 7 |
+
|
| 8 |
+
_This PR is opened automatically by the course CI. It is **non-blocking** — you do not need to merge it. The next nightly run will refresh this file._
|
| 9 |
+
|
| 10 |
+
## Summary
|
| 11 |
+
|
| 12 |
+
| Benchmark | Accuracy | Status |
|
| 13 |
+
|---|---:|---|
|
| 14 |
+
| Math | — | not run |
|
| 15 |
+
| Knowledge | — | not run |
|
| 16 |
+
| Multilingual | 0.5300 | ok |
|
| 17 |
+
| Safety | — | not run |
|
| 18 |
+
|
| 19 |
+
## Sample completions
|
| 20 |
+
|
| 21 |
+
_Prompts are intentionally omitted to avoid revealing benchmark contents. For multi-completion problems, only one completion is shown per sample._
|
| 22 |
+
|
| 23 |
+
### Multilingual
|
| 24 |
+
|
| 25 |
+
**Correct** (1 shown)
|
| 26 |
+
|
| 27 |
+
- **reference**: `B`
|
| 28 |
+
- **overall** (1/1 completions correct)
|
| 29 |
+
- **extracted** (✓): `B`
|
| 30 |
+
- **completion**:
|
| 31 |
+
|
| 32 |
+
```text
|
| 33 |
+
<think>
|
| 34 |
+
Okay, let's see. The question is about a make or buy decision in a business context. The options are A to D. I need to figure out which one the correct answer is.
|
| 35 |
+
|
| 36 |
+
First, I remember that make or buy refers to whether a company should produce a product internally or purchase it from an external supplier. The main consideration here is whether it's more cost-effective to produce it themselve
|
| 37 |
+
|
| 38 |
+
... [truncated 778 chars] ...
|
| 39 |
+
|
| 40 |
+
e quantity would be part of the purchasing decision, but not the primary problem of make or buy.
|
| 41 |
+
|
| 42 |
+
D. Proceeding with international operations. That's more about global operations rather than the internal make or buy decision. So D seems less relevant.
|
| 43 |
+
|
| 44 |
+
So the correct answer should be B. The problem is whether to produce internally or outsource a specific phase of work.
|
| 45 |
+
</think>
|
| 46 |
+
|
| 47 |
+
La decisione di "make or buy" si riferisce alla scelta tra produrre un prodotto internamente o affidarne la produzione a terzi. Questa decisione è focalizzata su una **scelta tra due opzioni**: produrre o acquistare.
|
| 48 |
+
|
| 49 |
+
**Razionalizzazione delle opzioni:**
|
| 50 |
+
- **A** è un aspetto secondario, poiché il prezzo di vendita non è il problema principale della decisione di make or buy.
|
| 51 |
+
- **B** è la risposta più diretta, poiché la decisione di "make or buy" si concentra sulla scelta tra produrre internamente o affidare a terzi una determinata fase del lavoro.
|
| 52 |
+
- **C** riguarda il quantitativo di materia prima, che è un aspetto del processo di acquisto, ma non della decisione principale.
|
| 53 |
+
- **D** riguarda operazioni internazionali, che non sono il focus della decisione di make or buy.
|
| 54 |
+
|
| 55 |
+
**Risposta corretta:**
|
| 56 |
+
$\boxed{B}$
|
| 57 |
+
```
|
| 58 |
+
|
| 59 |
+
**Incorrect** (1 shown)
|
| 60 |
+
|
| 61 |
+
- **reference**: `C`
|
| 62 |
+
- **overall** (0/1 completions correct)
|
| 63 |
+
- **extracted** (✗): `D`
|
| 64 |
+
- **completion**:
|
| 65 |
+
|
| 66 |
+
```text
|
| 67 |
+
<think>
|
| 68 |
+
嗯,我现在要解决这个题目。题目是说,用某种东西取代供应链,提高了产品_______的重要性,并对公司会产生_______的每一项活动进行根本性的重新设计。然后给出四个选项,我需要选择正确的答案。
|
| 69 |
+
|
| 70 |
+
首先,我需要理解题目中的各个部分。题目中的空格分别需要填入三个词:第一个空是“取代供应链”的东西,第二个空是“产品”被这个取代后的重要性提升的方面,第三个空是“公司”因为这个取代而对每一项活动进行重新设计的性质。
|
| 71 |
+
|
| 72 |
+
首先,我需要确定第一个空应该填什么。题目中的选项里有“全球生产网络”和“供应环”这两个词。供应链通常指的是整个从原材料到产品的流程,而全球生产网络(GPN)可能指的是一个更广泛的网络化生产结构,可能涉及多个地点的生产。而“供应环”可能指的是供应链的循环,或者更具体的某个环节?
|
| 73 |
+
|
| 74 |
+
不过,可能更准确的是,题目中的第一个空可能指的是“全球生产网络”或者“供应环”中的一个。比
|
| 75 |
+
|
| 76 |
+
... [truncated 821 chars] ...
|
| 77 |
+
|
| 78 |
+
或者,可能第二个空是“回收”,但回收可能不是产品的重要性提升的方面,而浪费可能更相关于资源利用,但题目中说公司对每一项活动进行重新设计,可能不是为了浪费,而是为了提高利润。
|
| 79 |
+
|
| 80 |
+
综上,可能选项D是正确的。
|
| 81 |
+
</think>
|
| 82 |
+
|
| 83 |
+
在本题中,我们需要判断三个空格应填入的词语,以准确表达语义逻辑。
|
| 84 |
+
|
| 85 |
+
---
|
| 86 |
+
|
| 87 |
+
### 一、理解题干结构
|
| 88 |
+
|
| 89 |
+
题干为:
|
| 90 |
+
|
| 91 |
+
> 用_______取代供应链提高了产品_______的重要性,并对公司会产生_______的每一项活动进行根本性的重新设计。
|
| 92 |
+
|
| 93 |
+
---
|
| 94 |
+
|
| 95 |
+
### 二、分析关键词与语义
|
| 96 |
+
|
| 97 |
+
1. **“取代供应链”**:
|
| 98 |
+
这里涉及的“取代”对象可能是**全球生产网络(GPN)**或**供应环**。
|
| 99 |
+
- **全球生产网络**(GPN)是一种���度集成的生产体系,强调全球布局与协同,常用于描述企业对供应链的重构。
|
| 100 |
+
- **供应环**(Supply Loop)则是指供应链中各环节的循环与互动,更侧重于资源流动与效率优化。
|
| 101 |
+
|
| 102 |
+
2. **“产品_______的重要性”**:
|
| 103 |
+
这个部分需要填入一个与“产品”相关、体现其价值或效率的词,可能是**效率**、**响应能力**、**灵活性**、**质量**等。
|
| 104 |
+
- 若选择“重新设计”,则可能是指对产品本身进行改进,但题干强调的是“对每一项活动进行根本性重新设计”,更倾向于流程层面的优化。
|
| 105 |
+
|
| 106 |
+
3. **“公司会产生_______的每一项活动进行根本性的重新设计”**:
|
| 107 |
+
这部分强调的是公司对活动的重新设计目的,通常是**提高效率、降低成本、增加利润**等。
|
| 108 |
+
- “利润”是最符合语义的选项。
|
| 109 |
+
|
| 110 |
+
---
|
| 111 |
+
|
| 112 |
+
### 三、选项分析
|
| 113 |
+
|
| 114 |
+
- **A. 全球生产网络,重新设计,利润**
|
| 115 |
+
- 逻辑上可行,但“重新设计”强调的是产品本身,而题干强调的是“对每一项活动进行重新设计”,因此“重新设计”可能不够准确。
|
| 116 |
+
|
| 117 |
+
- **B. 全球生产网络,回收,浪费**
|
| 118 |
+
- “回收”和“浪费”与“产品的重要性”关联性较弱,且“浪费”不是公司进行活动设计的常见目的。
|
| 119 |
+
|
| 120 |
+
- **C. 供应环,回收,浪费**
|
| 121 |
+
- “回收”与“浪费”同样不符合语义逻辑,且“供应环”作为供应链的循环概念,与“取代供应链”搭配不够自然。
|
| 122 |
+
|
| 123 |
+
- **D. 供应环,重新设计,利润**
|
| 124 |
+
- 这是最合理的选项。
|
| 125 |
+
- “供应环”取代供应链,意味着对供应链的重构,从而提升产品的**效率或响应能力**。
|
| 126 |
+
- “重新设计”指的是对活动的优化,符合题干中“每一项活动进行根本性重新设计”的描述。
|
| 127 |
+
- “利润”是公司进行活动设计的目的,符合逻辑。
|
| 128 |
+
|
| 129 |
+
---
|
| 130 |
+
|
| 131 |
+
### 四、最终结论
|
| 132 |
+
|
| 133 |
+
综合语义和逻辑,最符合题干要求的选项是:
|
| 134 |
+
|
| 135 |
+
$$
|
| 136 |
+
\boxed{D}
|
| 137 |
+
$$
|
| 138 |
+
```
|