Text Generation
Transformers
TensorBoard
Safetensors
qwen3
Generated from Trainer
trl
grpo
conversational
text-generation-inference
Instructions to use cs-552-2026-clankers-builder/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-clankers-builder/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-clankers-builder/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-clankers-builder/general_knowledge_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-clankers-builder/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-clankers-builder/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-clankers-builder/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-clankers-builder/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-clankers-builder/general_knowledge_model
- SGLang
How to use cs-552-2026-clankers-builder/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-clankers-builder/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-clankers-builder/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-clankers-builder/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-clankers-builder/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-clankers-builder/general_knowledge_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-clankers-builder/general_knowledge_model
Automated MNLP evaluation report (2026-06-11)
#1
by zechen-nlp - opened
- EVAL_REPORT.md +112 -0
EVAL_REPORT.md
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Automated MNLP evaluation report
|
| 2 |
+
|
| 3 |
+
- **Model repo:** [`cs-552-2026-clankers-builder/general_knowledge_model`](https://huggingface.co/cs-552-2026-clankers-builder/general_knowledge_model)
|
| 4 |
+
- **Owner(s):** group **clankers-builder**
|
| 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:** [`eb03b5e`](https://huggingface.co/cs-552-2026-clankers-builder/general_knowledge_model/commit/eb03b5eb5ff06748b64f806f802f3f14f518e69b)
|
| 13 |
+
- **Message:** Upload folder using huggingface_hub
|
| 14 |
+
- **Committed:** 2026-06-10T08:54:41+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**: `B`
|
| 34 |
+
- **overall** (1/1 completions correct)
|
| 35 |
+
- **extracted** (✓): `B`
|
| 36 |
+
- **completion**:
|
| 37 |
+
|
| 38 |
+
```text
|
| 39 |
+
Okay, let's see. I need to find the energy levels of four indistinguishable electrons in a one-dimensional infinite potential well. The question says to express the energy in terms of E, where E is given as π²ħ²/(2mL²).
|
| 40 |
+
|
| 41 |
+
First, I remember that for particles in a quantum well, the energy levels are quantized. Since the electrons are indistinguishable, I need to consider the Pauli exclusion princip
|
| 42 |
+
|
| 43 |
+
... [truncated 823 chars] ...
|
| 44 |
+
|
| 45 |
+
st excited state**, and **second excited state**. This implies the **total energy** of the system, not the individual energy levels of the electrons.
|
| 46 |
+
|
| 47 |
+
In this context, the **ground state** is when the **two lowest energy levels** are filled (n = 1 and n = 2), giving:
|
| 48 |
+
|
| 49 |
+
$$
|
| 50 |
+
\text{Ground State} = 2E + 2(4E) = 10E
|
| 51 |
+
$$
|
| 52 |
+
|
| 53 |
+
The **first excited state** is when the **next two energy levels** are filled (n = 2 and n = 3), giving:
|
| 54 |
+
|
| 55 |
+
$$
|
| 56 |
+
\text{First Excited State} = 2(4E) + 2(9E) = 8E + 18E = 26E
|
| 57 |
+
$$
|
| 58 |
+
|
| 59 |
+
However, this is still not among the choices.
|
| 60 |
+
|
| 61 |
+
---
|
| 62 |
+
|
| 63 |
+
### Final Consideration
|
| 64 |
+
|
| 65 |
+
Given the choices and the nature of the question, the most reasonable and consistent answer that matches the energy values in the context of **two electrons in the first level and two in the second** is:
|
| 66 |
+
|
| 67 |
+
- **Ground State**: $ 10E $
|
| 68 |
+
- **First Excited State**: $ 15E $
|
| 69 |
+
- **Second Excited State**: $ 18E $
|
| 70 |
+
|
| 71 |
+
These values are consistent with the assumption that the first excited state involves **one electron in the first level and three in the second**, and the second excited state involves **two in the second and two in the third**, even though the exact configuration is not explicitly stated.
|
| 72 |
+
|
| 73 |
+
---
|
| 74 |
+
|
| 75 |
+
### Final Answer
|
| 76 |
+
|
| 77 |
+
$$
|
| 78 |
+
\boxed{B}
|
| 79 |
+
$$
|
| 80 |
+
```
|
| 81 |
+
|
| 82 |
+
**Incorrect** (1 shown)
|
| 83 |
+
|
| 84 |
+
- **reference**: `A`
|
| 85 |
+
- **overall** (0/1 completions correct)
|
| 86 |
+
- **extracted** (✗): `J`
|
| 87 |
+
- **completion**:
|
| 88 |
+
|
| 89 |
+
```text
|
| 90 |
+
Okay, let's try to figure out this question about Nagel's account of moral luck. So, the question is asking why moral luck emerges according to Nagel. The choices are various options, and I need to pick the correct one.
|
| 91 |
+
|
| 92 |
+
First, I should recall what moral luck is. From what I remember, moral luck is the idea that the morality of an action doesn't depend on the person's character or intentions, but
|
| 93 |
+
|
| 94 |
+
... [truncated 823 chars] ...
|
| 95 |
+
|
| 96 |
+
I'm not sure if that's what Nagel is saying.
|
| 97 |
+
|
| 98 |
+
Alternatively, maybe the answer is E, that philosophers focus too much on the role of chance in human actions. If they focus too much on chance, then they might not consider the moral implications of the actions, leading to moral luck. But I'm not sure.
|
| 99 |
+
|
| 100 |
+
I think the correct answer is J, but I'm not entirely certain. However, given the options, I'll go with J.
|
| 101 |
+
</think>
|
| 102 |
+
|
| 103 |
+
**Moral luck** is the idea that the moral evaluation of an action is not necessarily dependent on the agent's intentions or character, but rather on the circumstances in which the action occurs. This concept challenges the notion that moral responsibility is tied to the individual's conscious choices or intentions.
|
| 104 |
+
|
| 105 |
+
Nagel, in his philosophical account, argues that moral luck arises because **our moral theories are hopelessly off track**—they fail to account for the role of chance in shaping the moral evaluation of actions. This means that even if an action is performed with clear intent or responsibility, the outcome (and thus the moral judgment) may be influenced by factors beyond the agent's control, such as luck or chance.
|
| 106 |
+
|
| 107 |
+
Thus, the correct answer is:
|
| 108 |
+
|
| 109 |
+
$$
|
| 110 |
+
\boxed{J}
|
| 111 |
+
$$
|
| 112 |
+
```
|