Instructions to use cs-552-2026-mnlplus/general_knowledge_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs-552-2026-mnlplus/general_knowledge_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cs-552-2026-mnlplus/general_knowledge_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-mnlplus/general_knowledge_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-mnlplus/general_knowledge_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=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-mnlplus/general_knowledge_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-mnlplus/general_knowledge_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-mnlplus/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-mnlplus/general_knowledge_model
- SGLang
How to use cs-552-2026-mnlplus/general_knowledge_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-mnlplus/general_knowledge_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-mnlplus/general_knowledge_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-mnlplus/general_knowledge_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-mnlplus/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-mnlplus/general_knowledge_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-mnlplus/general_knowledge_model
Update Automated MNLP evaluation report (2026-05-26)
Browse files- EVAL_REPORT.md +17 -54
EVAL_REPORT.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-mnlplus/general_knowledge_model`](https://huggingface.co/cs-552-2026-mnlplus/general_knowledge_model)
|
| 4 |
- **Owner(s):** group **mnlplus**
|
| 5 |
-
- **Generated at:** 2026-05-
|
| 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** β you do not need to merge it. The next nightly run will refresh this file._
|
|
@@ -12,7 +12,7 @@ _This PR is opened automatically by the course CI. It is **non-blocking** β yo
|
|
| 12 |
| Benchmark | Accuracy | Status |
|
| 13 |
|---|---:|---|
|
| 14 |
| Math | β | not run |
|
| 15 |
-
| Knowledge | 0.
|
| 16 |
| Multilingual | β | not run |
|
| 17 |
| Safety | β | not run |
|
| 18 |
|
|
@@ -24,74 +24,37 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
-
- **reference**: `
|
| 28 |
- **overall** (1/1 completions correct)
|
| 29 |
-
- **extracted** (β): `
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
<think>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
</think>
|
| 35 |
|
| 36 |
-
\boxed{
|
| 37 |
```
|
| 38 |
|
| 39 |
**Incorrect** (1 shown)
|
| 40 |
|
| 41 |
- **reference**: `B`
|
| 42 |
- **overall** (0/1 completions correct)
|
| 43 |
-
- **extracted** (β): `
|
| 44 |
- **completion**:
|
| 45 |
|
| 46 |
```text
|
| 47 |
<think>
|
| 48 |
-
The
|
| 49 |
-
|
| 50 |
-
First, I need to recall the divergence theorem, which relates the volume inte
|
| 51 |
-
|
| 52 |
-
... [truncated 823 chars] ...
|
| 53 |
-
|
| 54 |
-
ield $\vec{f}(r)$ is directed purely along the radial direction, meaning it points outward from the origin, and its magnitude decreases as $f(r) = \frac{1}{r^2}$. In spherical coordinates, this corresponds to a radial vector field.
|
| 55 |
-
|
| 56 |
-
---
|
| 57 |
-
|
| 58 |
-
### Step 2: Use the Divergence Theorem
|
| 59 |
-
|
| 60 |
-
The divergence theorem relates the volume integral of the divergence of a vector field to the flux of the field through the surface of the region. It states:
|
| 61 |
-
|
| 62 |
-
$$
|
| 63 |
-
\iiint_V (\nabla \cdot \vec{f}) \, dV = \iint_S \vec{f} \cdot d\vec{S}
|
| 64 |
-
$$
|
| 65 |
-
|
| 66 |
-
where $V$ is the region enclosed by the surface $S$.
|
| 67 |
-
|
| 68 |
-
---
|
| 69 |
-
|
| 70 |
-
### Step 3: Compute the Divergence
|
| 71 |
-
|
| 72 |
-
For a radial vector field in spherical coordinates, the divergence is:
|
| 73 |
-
|
| 74 |
-
$$
|
| 75 |
-
\nabla \cdot \vec{f} = \frac{1}{r^2} \frac{d}{dr}(r^2 f(r)) = \frac{1}{r^2} \frac{d}{dr}(r^2 \cdot \frac{1}{r^2}) = \frac{1}{r^2} \frac{d}{dr}(1) = 0
|
| 76 |
-
$$
|
| 77 |
-
|
| 78 |
-
Thus, the divergence of the vector field is **zero** everywhere except at the origin, where the field is undefined.
|
| 79 |
-
|
| 80 |
-
---
|
| 81 |
-
|
| 82 |
-
### Step 4: Evaluate the Volume Integral
|
| 83 |
-
|
| 84 |
-
Since the divergence is zero everywhere, the volume integral of the divergence over any region is also zero:
|
| 85 |
-
|
| 86 |
-
$$
|
| 87 |
-
\iiint_V (\nabla \cdot \vec{f}) \, dV = 0
|
| 88 |
-
$$
|
| 89 |
-
|
| 90 |
-
---
|
| 91 |
-
|
| 92 |
-
### Final Answer
|
| 93 |
|
| 94 |
-
|
| 95 |
-
\boxed{C}
|
| 96 |
-
$$
|
| 97 |
```
|
|
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-mnlplus/general_knowledge_model`](https://huggingface.co/cs-552-2026-mnlplus/general_knowledge_model)
|
| 4 |
- **Owner(s):** group **mnlplus**
|
| 5 |
+
- **Generated at:** 2026-05-26T12:29:10+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** β you do not need to merge it. The next nightly run will refresh this file._
|
|
|
|
| 12 |
| Benchmark | Accuracy | Status |
|
| 13 |
|---|---:|---|
|
| 14 |
| Math | β | not run |
|
| 15 |
+
| Knowledge | 0.4100 | ok |
|
| 16 |
| Multilingual | β | not run |
|
| 17 |
| Safety | β | not run |
|
| 18 |
|
|
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
+
- **reference**: `I`
|
| 28 |
- **overall** (1/1 completions correct)
|
| 29 |
+
- **extracted** (β): `I`
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
<think>
|
| 34 |
+
To determine the probability of the event $\{M \geq 5\}$, we need to calculate the probability that $S_0 = 0$, $S_1 = 0$, $S_2 = 0$, $S_3 = 0$, $S_4 = 0$, and $S_5 = 0$.
|
| 35 |
+
We can calculate the probability of each of these events as follows:
|
| 36 |
+
- $P(S_0 = 0) = 1$
|
| 37 |
+
- $P(S_1 = 0) = P(S_0 + 1 = 0) + P(S_0 - 1 = 0) = \frac{1}{4} + \frac{1}{4} = \frac{1}{2}$
|
| 38 |
+
- $P(S_2 = 0) = P(S_1 + 1 = 0) + P(S_1 - 1 = 0) = \frac{1}{4} + \frac{1}{4} = \frac{1}{2}$
|
| 39 |
+
- $P(S_3 = 0) = P(S_2 + 1 = 0) + P(S_2 - 1 = 0) = \frac{1}{4} + \frac{1}{4} = \frac{1}{2}$
|
| 40 |
+
- $P(S_4 = 0) = P(S_3 + 1 = 0) + P(S_3 - 1 = 0) = \frac{1}{4} + \frac{1}{4} = \frac{1}{2}$
|
| 41 |
+
- $P(S_5 = 0) = P(S_4 + 1 = 0) + P(S_4 - 1 = 0) = \frac{1}{4} + \frac{1}{4} = \frac{1}{2}$
|
| 42 |
</think>
|
| 43 |
|
| 44 |
+
\boxed{I}
|
| 45 |
```
|
| 46 |
|
| 47 |
**Incorrect** (1 shown)
|
| 48 |
|
| 49 |
- **reference**: `B`
|
| 50 |
- **overall** (0/1 completions correct)
|
| 51 |
+
- **extracted** (β): `D`
|
| 52 |
- **completion**:
|
| 53 |
|
| 54 |
```text
|
| 55 |
<think>
|
| 56 |
+
The correct answer is D.
|
| 57 |
+
</think>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
|
| 59 |
+
\boxed{D}
|
|
|
|
|
|
|
| 60 |
```
|