Text Generation
Transformers
Safetensors
English
qwen3
general-knowledge
reasoning
sft
cs-552
mnlp
conversational
text-generation-inference
Instructions to use cs-552-2026-aaty/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-aaty/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-aaty/general_knowledge_model", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cs-552-2026-aaty/general_knowledge_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-aaty/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-aaty/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-aaty/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-aaty/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-aaty/general_knowledge_model
- SGLang
How to use cs-552-2026-aaty/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-aaty/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-aaty/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-aaty/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-aaty/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-aaty/general_knowledge_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-aaty/general_knowledge_model
Automated MNLP evaluation report (2026-06-11)
#1
by zechen-nlp - opened
- EVAL_REPORT.md +79 -0
EVAL_REPORT.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Automated MNLP evaluation report
|
| 2 |
+
|
| 3 |
+
- **Model repo:** [`cs-552-2026-aaty/general_knowledge_model`](https://huggingface.co/cs-552-2026-aaty/general_knowledge_model)
|
| 4 |
+
- **Owner(s):** group **aaty**
|
| 5 |
+
- **Generated at:** 2026-06-11T06:23:10+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** — you do not need to merge it. The next nightly run will refresh this file._
|
| 9 |
+
|
| 10 |
+
## Evaluated checkpoint
|
| 11 |
+
|
| 12 |
+
- **Commit:** [`50235d1`](https://huggingface.co/cs-552-2026-aaty/general_knowledge_model/commit/50235d1616c3283be3bc7816dcfe3058c1fcabf5)
|
| 13 |
+
- **Message:** Update README.md
|
| 14 |
+
- **Committed:** 2026-06-10T11:49:34+00:00
|
| 15 |
+
|
| 16 |
+
## Summary
|
| 17 |
+
|
| 18 |
+
| Benchmark | Accuracy | Status |
|
| 19 |
+
|---|---:|---|
|
| 20 |
+
| Math | — | not run |
|
| 21 |
+
| Knowledge | 0.4300 | ok |
|
| 22 |
+
| Multilingual | — | not run |
|
| 23 |
+
| Safety | — | not run |
|
| 24 |
+
|
| 25 |
+
## Sample completions
|
| 26 |
+
|
| 27 |
+
_Prompts are intentionally omitted to avoid revealing benchmark contents. For multi-completion problems, only one completion is shown per sample._
|
| 28 |
+
|
| 29 |
+
### Knowledge
|
| 30 |
+
|
| 31 |
+
**Correct** (1 shown)
|
| 32 |
+
|
| 33 |
+
- **reference**: `A`
|
| 34 |
+
- **overall** (1/1 completions correct)
|
| 35 |
+
- **extracted** (✓): `A`
|
| 36 |
+
- **completion**:
|
| 37 |
+
|
| 38 |
+
```text
|
| 39 |
+
<think>
|
| 40 |
+
To compare the paramagnetic coupling term with the hydrogen atom transition energy, we need to calculate both quantities.
|
| 41 |
+
|
| 42 |
+
The hydrogen atom transition energy is given by the Rydberg formula:
|
| 43 |
+
$$\Delta E = \frac{hc}{\lambda}$$
|
| 44 |
+
where $h$ is Planck's constant, $c$ is the speed of light, and $\lambda = 0.4861\mu m = 486.1 \times 10^{-9}m$.
|
| 45 |
+
|
| 46 |
+
Using the values $h = 6.626 \times 10^{-34}J \cdot s$, $c = 3.00 \times 10^8m/s$:
|
| 47 |
+
$$\Delta E = \frac{(6.626 \times 10^{-34})(3.00 \times 10^8)}{486.1 \times 10^{-9}} = \frac{1.988 \times 10^{-25}}{486.1 \times 10^{-9}} = 4.08 \times 10^{-19}J$$
|
| 48 |
+
|
| 49 |
+
The paramagnetic coupling term is given by:
|
| 50 |
+
$$\langle H \rangle = \mu_B \cdot B \cdot m$$
|
| 51 |
+
where $\mu_B = 9.27 \times 10^{-24}J/T$ is the Bohr magneton.
|
| 52 |
+
|
| 53 |
+
For small values of $m$, the maximum value of $m$ is approximately 1 (for $m = 1$):
|
| 54 |
+
$$\langle H \rangle = (9.27 \times 10^{-24})(1)(1) = 9.27 \times 10^{-24}J$$
|
| 55 |
+
|
| 56 |
+
Comparing the two:
|
| 57 |
+
$$\langle H \rangle = 9.27 \times 10^{-24}J$$
|
| 58 |
+
$$\Delta E = 4.08 \times 10^{-19}J$$
|
| 59 |
+
|
| 60 |
+
Clearly, $\langle H \rangle \ll \Delta E$ because $9.27 \times 10^{-24}J$ is much smaller than $4.08 \times 10^{-19}J$. The paramagnetic coupling term is much smaller than the hydrogen atom transition energy. The answer is $\langle H \rangle \ll \Delta E$.
|
| 61 |
+
</think>
|
| 62 |
+
|
| 63 |
+
The answer is \boxed{A}
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
**Incorrect** (1 shown)
|
| 67 |
+
|
| 68 |
+
- **reference**: `A`
|
| 69 |
+
- **overall** (0/1 completions correct)
|
| 70 |
+
- **extracted** (✗): `H`
|
| 71 |
+
- **completion**:
|
| 72 |
+
|
| 73 |
+
```text
|
| 74 |
+
<think>
|
| 75 |
+
Nagel's account of moral luck is a philosophical response to the problem of moral responsibility and the role of chance in human actions. Nagel argues that moral luck arises because our moral theories are hopelessly off track. He contends that we cannot adequately account for the role of chance in human actions and decisions. According to Nagel, moral luck occurs when we fail to recognize that our moral responsibility is not determined by the actual outcomes of our actions, but rather by the circumstances in which those actions occur. When we fail to properly account for the role of chance in our moral theories, we end up assigning moral responsibility to people based on outcomes that are not genuinely determined by their actions themselves. This is the core problem Nagel identifies: our theories of human action are hopelessly off track because they don't properly incorporate the element of luck that actually determines moral responsibility. The answer is H.
|
| 76 |
+
</think>
|
| 77 |
+
|
| 78 |
+
The answer is \boxed{H}
|
| 79 |
+
```
|