Instructions to use cs-552-2026-catma/general_knowledge_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cs-552-2026-catma/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-catma/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-catma/general_knowledge_model")
model = AutoModelForCausalLM.from_pretrained("cs-552-2026-catma/general_knowledge_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-catma/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-catma/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-catma/general_knowledge_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cs-552-2026-catma/general_knowledge_model

SGLang

How to use cs-552-2026-catma/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-catma/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-catma/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-catma/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-catma/general_knowledge_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cs-552-2026-catma/general_knowledge_model with Docker Model Runner:
```
docker model run hf.co/cs-552-2026-catma/general_knowledge_model
```

Automated MNLP evaluation report (2026-05-19)

by zechen-nlp - opened May 18

base: refs/heads/main

←

from: refs/pr/5

Discussion Files changed

-83

Files changed (1) hide show

EVAL_REPORT.md +8 -83

EVAL_REPORT.md CHANGED Viewed

@@ -2,7 +2,7 @@
 - **Model repo:** [`cs-552-2026-catma/general_knowledge_model`](https://huggingface.co/cs-552-2026-catma/general_knowledge_model)
 - **Owner(s):** group **catma**
-- **Generated at:** 2026-05-17T04:52:19+00:00 (UTC)
 - **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci)
 _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._
@@ -12,7 +12,7 @@ _This PR is opened automatically by the course CI. It is **non-blocking** — yo
 | Benchmark | Accuracy | Status |
 |---|---:|---|
 | Math | — | not run |
-| Knowledge | 0.3200 | ok |
 | Multilingual | — | not run |
 | Safety | — | not run |
@@ -24,97 +24,22 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
 **Correct** (1 shown)
-- **reference**: `F`
 - **overall** (1/1 completions correct)
-- **extracted** (✓): `F`
 - **completion**:
     ```text
-    To estimate the largest possible percentage error in the computed value of $ S $ using differentials, we start with the given formula:
-    $$
-    S = 0.1091 \cdot w^{0.425} \cdot h^{0.725}
-    $$
-    We are given that the measurement errors for both $ w $ and $ h $ are no greater than $ 2\% $, and we are to estimate the largest possible percentage error in $ S $.
-    ---
-    ### Step 1: Use the differential
-    The diff
-    ... [truncated 305 chars] ...
-    cdot 0.725 \cdot w^{0.425} \cdot h^{-0.275}
-    $$
-    So,
-    $$
-    dS = 0.1091 \cdot 0.425 \cdot w^{-0.575} \cdot h^{0.725} \cdot dw + 0.1091 \cdot 0.725 \cdot w^{0.425} \cdot h^{-0.275} \cdot dh
-    $$
-    ---
-    ### Step 2: Express the percentage error
-    The percentage error in $ S $ is approximately:
-    $$
-    \frac{dS}{S} \approx \left( \frac{\partial S}{\partial w} \cdot \frac{dw}{w} + \frac{\partial S}{\partial h} \cdot \frac{dh}{h} \right) \cdot \frac{1}{S}
-    $$
-    But since $ S $ is a function of $ w $ and $ h $, we can write:
-    $$
-    \frac{dS}{S} \approx \left( \frac{\partial S}{\partial w} \cdot \frac{dw}{w} + \frac{\partial S}{\partial h} \cdot \frac{dh}{h} \right)
-    $$
-    Now, substitute the partial derivatives:
-    $$
-    \frac{dS}{S} \approx \left( 0.425 \cdot \frac{dw}{w} + 0.725 \cdot \frac{dh}{h} \right)
-    $$
-    ---
-    ### Step 3: Use the given error bounds
-    We are told that the measurement errors for $ w $ and $ h $ are no greater than $ 2\% $, so:
-    $$
-    \frac{dw}{w} \leq 0.02, \quad \frac{dh}{h} \leq 0.02
-    $$
-    So,
-    $$
-    \frac{dS}{S} \leq 0.425 \cdot 0.02 + 0.725 \cdot 0.02 = 0.0085 + 0.0145 = 0.023
-    $$
-    Thus, the largest possible percentage error in $ S $ is:
-    $$
-    \boxed{2.3\%}
-    $$
-    ---
-    ### Final Answer:
-    $$
-    \boxed{F}
-    $$
     ```
 **Incorrect** (1 shown)
-- **reference**: `C`
 - **overall** (0/1 completions correct)
-- **extracted** (✗): `D`
 - **completion**:
     ```text
-    \boxed{D}
     ```

 - **Model repo:** [`cs-552-2026-catma/general_knowledge_model`](https://huggingface.co/cs-552-2026-catma/general_knowledge_model)
 - **Owner(s):** group **catma**
+- **Generated at:** 2026-05-19T03:22:52+00:00 (UTC)
 - **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci)
 _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._
 | Benchmark | Accuracy | Status |
 |---|---:|---|
 | Math | — | not run |
+| Knowledge | 0.3400 | ok |
 | Multilingual | — | not run |
 | Safety | — | not run |
 **Correct** (1 shown)
+- **reference**: `A`
 - **overall** (1/1 completions correct)
+- **extracted** (✓): `A`
 - **completion**:
     ```text
+    \boxed{A}
     ```
 **Incorrect** (1 shown)
+- **reference**: `I`
 - **overall** (0/1 completions correct)
+- **extracted** (✗): `B`
 - **completion**:
     ```text
+    \boxed{B}
     ```