Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
grpo
conversational
text-generation-inference
Instructions to use cs-552-2026-MMRF/multilingual_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-MMRF/multilingual_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-MMRF/multilingual_model") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cs-552-2026-MMRF/multilingual_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-MMRF/multilingual_model", device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use cs-552-2026-MMRF/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-MMRF/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-MMRF/multilingual_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-MMRF/multilingual_model
- SGLang
How to use cs-552-2026-MMRF/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-MMRF/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-MMRF/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-MMRF/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-MMRF/multilingual_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-MMRF/multilingual_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-MMRF/multilingual_model
Update Automated MNLP evaluation report (2026-06-11)
Browse files- EVAL_REPORT.md +32 -29
EVAL_REPORT.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-MMRF/multilingual_model`](https://huggingface.co/cs-552-2026-MMRF/multilingual_model)
|
| 4 |
- **Owner(s):** group **MMRF**
|
| 5 |
-
- **Generated at:** 2026-06-
|
| 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._
|
|
@@ -19,7 +19,7 @@ _This PR is opened automatically by the course CI. It is **non-blocking** — yo
|
|
| 19 |
|---|---:|---|
|
| 20 |
| Math | — | not run |
|
| 21 |
| Knowledge | — | not run |
|
| 22 |
-
| Multilingual | 0.
|
| 23 |
| Safety | — | not run |
|
| 24 |
|
| 25 |
## Sample completions
|
|
@@ -30,66 +30,69 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 30 |
|
| 31 |
**Correct** (1 shown)
|
| 32 |
|
| 33 |
-
- **reference**: `
|
| 34 |
- **overall** (1/1 completions correct)
|
| 35 |
-
- **extracted** (✓): `
|
| 36 |
- **completion**:
|
| 37 |
|
| 38 |
```text
|
| 39 |
<think>
|
| 40 |
-
Okay, let's
|
| 41 |
|
| 42 |
-
First, I need to recall what
|
| 43 |
|
| 44 |
-
... [truncated
|
| 45 |
|
| 46 |
-
|
|
|
|
| 47 |
|
| 48 |
-
|
| 49 |
|
| 50 |
-
|
| 51 |
-
</think>
|
| 52 |
|
| 53 |
-
|
| 54 |
|
| 55 |
-
|
| 56 |
|
|
|
|
| 57 |
$$
|
| 58 |
-
\boxed{
|
| 59 |
$$
|
| 60 |
```
|
| 61 |
|
| 62 |
**Incorrect** (1 shown)
|
| 63 |
|
| 64 |
-
- **reference**: `
|
| 65 |
- **overall** (0/1 completions correct)
|
| 66 |
-
- **extracted** (✗): `
|
| 67 |
- **completion**:
|
| 68 |
|
| 69 |
```text
|
| 70 |
<think>
|
| 71 |
-
Okay, let's
|
| 72 |
|
| 73 |
-
First, I need to recall
|
| 74 |
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
s a client's account with full power of attorney, then they have more responsibility. The rules might apply here.
|
| 78 |
|
| 79 |
-
|
| 80 |
|
| 81 |
-
|
|
|
|
| 82 |
|
| 83 |
-
|
|
|
|
| 84 |
|
| 85 |
-
|
| 86 |
-
|
| 87 |
|
| 88 |
-
|
|
|
|
| 89 |
|
| 90 |
-
|
|
|
|
| 91 |
|
| 92 |
$$
|
| 93 |
-
\boxed{
|
| 94 |
$$
|
| 95 |
```
|
|
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-MMRF/multilingual_model`](https://huggingface.co/cs-552-2026-MMRF/multilingual_model)
|
| 4 |
- **Owner(s):** group **MMRF**
|
| 5 |
+
- **Generated at:** 2026-06-11T04:19:46+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._
|
|
|
|
| 19 |
|---|---:|---|
|
| 20 |
| Math | — | not run |
|
| 21 |
| Knowledge | — | not run |
|
| 22 |
+
| Multilingual | 0.5500 | ok |
|
| 23 |
| Safety | — | not run |
|
| 24 |
|
| 25 |
## Sample completions
|
|
|
|
| 30 |
|
| 31 |
**Correct** (1 shown)
|
| 32 |
|
| 33 |
+
- **reference**: `C`
|
| 34 |
- **overall** (1/1 completions correct)
|
| 35 |
+
- **extracted** (✓): `C`
|
| 36 |
- **completion**:
|
| 37 |
|
| 38 |
```text
|
| 39 |
<think>
|
| 40 |
+
Okay, let's try to figure out this question. The user is asking about the Pleistocene epoch and a specific landmass that emerged during that time. The question mentions that around 28,000 to 18,000 years ago, sea levels were much lower, which caused a landmass called __________ to become visible in Siberia's east. Then, the period is called __________.
|
| 41 |
|
| 42 |
+
First, I need to recall what the Ple
|
| 43 |
|
| 44 |
+
... [truncated 823 chars] ...
|
| 45 |
|
| 46 |
+
ंगिया", then option C is correct. But if "बेरिंजिया" is a different term, then maybe another option. However, given the options, I think the correct answer is C. Alternatively, option B has Beringia and "स्वर्गीय बेरिंगियन काल" which might be a mistranslation. The correct term is "Beringian period" but maybe the option is using "स्वर्गीय" as a translation. But the correct answer is Beringia and the Late Glacial Maximum. So option C is correct.
|
| 47 |
+
</think>
|
| 48 |
|
| 49 |
+
The question refers to a geological period during which sea levels were significantly lower, exposing a landmass in Siberia's east. This period is known for the emergence of Beringia, a land bridge connecting Asia and North America. The Late Glacial Maximum (LGM) is a well-documented period in the Pleistocene epoch, occurring around 20,000 to 18,000 years ago. This period is characterized by the retreat of glaciers and the exposure of Beringia, which is a key feature of the Pleistocene.
|
| 50 |
|
| 51 |
+
Among the given options:
|
|
|
|
| 52 |
|
| 53 |
+
- **Option C** correctly identifies Beringia as the landmass and the Late Glacial Maximum as the period, aligning with the timeline and geological context described in the question.
|
| 54 |
|
| 55 |
+
---
|
| 56 |
|
| 57 |
+
**Final Answer:**
|
| 58 |
$$
|
| 59 |
+
\boxed{C}
|
| 60 |
$$
|
| 61 |
```
|
| 62 |
|
| 63 |
**Incorrect** (1 shown)
|
| 64 |
|
| 65 |
+
- **reference**: `D`
|
| 66 |
- **overall** (0/1 completions correct)
|
| 67 |
+
- **extracted** (✗): `A`
|
| 68 |
- **completion**:
|
| 69 |
|
| 70 |
```text
|
| 71 |
<think>
|
| 72 |
+
Okay, let's tackle this question. The question is about the quality indicator used as a basis for comparing the quality of products. The options are A to D.
|
| 73 |
|
| 74 |
+
First, I need to recall what each of these terms means. The question is in Russian, so I should make sure I understand the terms correctly.
|
| 75 |
|
| 76 |
+
The key here is to identify which of these terms refers to the base quality indicator used i
|
|
|
|
|
|
|
| 77 |
|
| 78 |
+
... [truncated 823 chars] ...
|
| 79 |
|
| 80 |
+
t of importance of quality indicator)**
|
| 81 |
+
This refers to the **weight or significance** assigned to a quality indicator when evaluating products. It is a **measure of importance**, not the actual value of the indicator itself. However, it is **used as a basis for comparison** in quality evaluation frameworks.
|
| 82 |
|
| 83 |
+
- **B. Коэффициент сортности продукции (Coefficient of product grade)**
|
| 84 |
+
This relates to the **grading of products**, which is not directly tied to the **value of a quality indicator** for comparison.
|
| 85 |
|
| 86 |
+
- **C. Коэффициент дефектности продукции (Coefficient of product defectiveness)**
|
| 87 |
+
This measures the **proportion of defective items**, which is a **measure of defectiveness**, not the value of a quality indicator for comparison.
|
| 88 |
|
| 89 |
+
- **D. Индекс дефектности продукции (Index of product defectiveness)**
|
| 90 |
+
This is a **quantitative measure** of defectiveness, similar to the coefficient, but it is **not the value of the quality indicator** used for comparison.
|
| 91 |
|
| 92 |
+
### Conclusion:
|
| 93 |
+
The **value of the quality indicator** used for comparison is not a coefficient or index but rather the **importance** (weight) assigned to it. Therefore, **A** is the correct answer.
|
| 94 |
|
| 95 |
$$
|
| 96 |
+
\boxed{A}
|
| 97 |
$$
|
| 98 |
```
|