Instructions to use cs-552-2026-claude-bots/multilingual_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-claude-bots/multilingual_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-claude-bots/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-claude-bots/multilingual_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-claude-bots/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-claude-bots/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-claude-bots/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-claude-bots/multilingual_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-claude-bots/multilingual_model
- SGLang
How to use cs-552-2026-claude-bots/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-claude-bots/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-claude-bots/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-claude-bots/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-claude-bots/multilingual_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-claude-bots/multilingual_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-claude-bots/multilingual_model
Automated MNLP evaluation report (2026-06-06)
#2
by zechen-nlp - opened
- EVAL_REPORT.md +9 -7
EVAL_REPORT.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-claude-bots/multilingual_model`](https://huggingface.co/cs-552-2026-claude-bots/multilingual_model)
|
| 4 |
- **Owner(s):** group **claude-bots**
|
| 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._
|
|
@@ -13,7 +13,7 @@ _This PR is opened automatically by the course CI. It is **non-blocking** — yo
|
|
| 13 |
|---|---:|---|
|
| 14 |
| Math | — | not run |
|
| 15 |
| Knowledge | — | not run |
|
| 16 |
-
| Multilingual | 0.
|
| 17 |
| Safety | — | not run |
|
| 18 |
|
| 19 |
## Sample completions
|
|
@@ -30,7 +30,8 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
-
|
|
|
|
| 34 |
</think>
|
| 35 |
|
| 36 |
Final answer: \boxed{C}
|
|
@@ -38,14 +39,15 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 38 |
|
| 39 |
**Incorrect** (1 shown)
|
| 40 |
|
| 41 |
-
- **reference**: `
|
| 42 |
- **overall** (0/1 completions correct)
|
| 43 |
-
- **extracted** (✗): `
|
| 44 |
- **completion**:
|
| 45 |
|
| 46 |
```text
|
| 47 |
-
|
|
|
|
| 48 |
</think>
|
| 49 |
|
| 50 |
-
Final answer: \boxed{
|
| 51 |
```
|
|
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-claude-bots/multilingual_model`](https://huggingface.co/cs-552-2026-claude-bots/multilingual_model)
|
| 4 |
- **Owner(s):** group **claude-bots**
|
| 5 |
+
- **Generated at:** 2026-06-06T17:23:37+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._
|
|
|
|
| 13 |
|---|---:|---|
|
| 14 |
| Math | — | not run |
|
| 15 |
| Knowledge | — | not run |
|
| 16 |
+
| Multilingual | 0.5800 | ok |
|
| 17 |
| Safety | — | not run |
|
| 18 |
|
| 19 |
## Sample completions
|
|
|
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
+
<think>
|
| 34 |
+
The tax multiplier measures how much equilibrium income changes for a given change in taxes. The formula for the simple tax multiplier is typically expressed as -MPC / (1 - MPC), where MPC stands for the marginal propensity to consume. This mathematical relationship indicates that the magnitude of the tax multiplier depends directly on the value of the MPC. When the marginal propensity to consume increases, households spend a larger fraction of any additional income rather than saving it. Consequently, this higher spending further amplifies the initial effect of tax changes on aggregate demand. Therefore, an increase in the MPC leads to a larger absolute value for the tax multiplier. Option A suggests increasing the marginal propensity to save, which would decrease the MPC because saving plus consumption equals one, making the result smaller. Option B describes a reduction in the expenditure multiplier, which contradicts standard economic theory regarding these two distinct multipliers. Option D refers to reserve ratios, which primarily affect monetary policy and the money supply rather than the direct fiscal impact of taxation. Thus, the statement that increasing the marginal propensity to consume increases the size of the tax multiplier is theoretically accurate based on macroeconomic principles.
|
| 35 |
</think>
|
| 36 |
|
| 37 |
Final answer: \boxed{C}
|
|
|
|
| 39 |
|
| 40 |
**Incorrect** (1 shown)
|
| 41 |
|
| 42 |
+
- **reference**: `D`
|
| 43 |
- **overall** (0/1 completions correct)
|
| 44 |
+
- **extracted** (✗): `C`
|
| 45 |
- **completion**:
|
| 46 |
|
| 47 |
```text
|
| 48 |
+
<think>
|
| 49 |
+
The scenario describes a contract dispute involving a computer retailer ordering 100 computers from a manufacturer. The key legal issue here involves the interpretation of "acceptance" (swayakarta) in a contract where terms were explicitly limited by the original order form. In contract law, a party must accept a proposal to form a binding agreement. However, when there is ambiguity regarding what constitutes acceptance, courts often look at whether the offeree's actions demonstrate clear acceptance of the specific terms set forth at the time of the offer. Here, the manufacturer sent a confirmation agreeing to two deliveries but also stated that "shipment will occur over two deliveries." This phrasing creates a significant ambiguity about whether the promise to ship on August 1st was fully accepted as part of the final delivery terms or merely a condition precedent. Because the original order form clearly limited acceptance to the terms of that specific form, and the manufacturer's response added additional terms without clarifying them, the retailer's right to reject the shipment after August 1st stands unchallenged under standard contract principles. Option A suggests a narrow difference existed which does not override the express terms. Option B focuses on timing rather than the core contract formation issue. Option D implies ratification after silence, which is generally insufficient without affirmative conduct like shipment. Therefore, the manufacturer will likely win because the terms were explicitly limited by the order form.
|
| 50 |
</think>
|
| 51 |
|
| 52 |
+
Final answer: \boxed{C}
|
| 53 |
```
|