Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
sft
trl
conversational
text-generation-inference
Instructions to use cs-552-2026-flab/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-flab/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-flab/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-flab/general_knowledge_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-flab/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-flab/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-flab/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-flab/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-flab/general_knowledge_model
- SGLang
How to use cs-552-2026-flab/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-flab/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-flab/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-flab/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-flab/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-flab/general_knowledge_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-flab/general_knowledge_model
Update Automated MNLP evaluation report (2026-06-02)
Browse files- EVAL_REPORT.md +36 -70
EVAL_REPORT.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-flab/general_knowledge_model`](https://huggingface.co/cs-552-2026-flab/general_knowledge_model)
|
| 4 |
- **Owner(s):** group **flab**
|
| 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._
|
|
@@ -24,74 +24,51 @@ _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** (✓): `
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
<think>
|
| 34 |
-
Okay, let's
|
| 35 |
|
| 36 |
-
|
| 37 |
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
$$
|
| 41 |
-
\text{pH} = \text{p}K_{a2} + \log\left(\frac{[\text{HPO}_4^{2-}]}{[\text{H}_2\text{PO}_4^-]}\right)
|
| 42 |
-
$$
|
| 43 |
-
|
| 44 |
-
- **pKa₂** (from the given Ka₂ = 6.2 × 10⁻⁸):
|
| 45 |
-
$$
|
| 46 |
-
\text{p}K_{a2} = -\log(6.2 \times 10^{-8}) \approx 7.21
|
| 47 |
-
$$
|
| 48 |
-
|
| 49 |
-
- **Ratio:**
|
| 50 |
-
$$
|
| 51 |
-
\frac{[\text{HPO}_4^{2-}]}{[\text{H}_2\text{PO}_4^-]} = \frac{0.0282}{0.036735} \approx 0.768
|
| 52 |
-
$$
|
| 53 |
-
|
| 54 |
-
- **pH:**
|
| 55 |
-
$$
|
| 56 |
-
\text{pH} = 7.21 + \log(0.768) \approx 7.21 - 0.113 = 7.097
|
| 57 |
-
$$
|
| 58 |
-
|
| 59 |
-
---
|
| 60 |
|
| 61 |
-
|
| 62 |
|
| 63 |
-
|
| 64 |
|
| 65 |
$$
|
| 66 |
-
\text{
|
| 67 |
$$
|
| 68 |
|
| 69 |
-
The
|
| 70 |
|
| 71 |
$$
|
| 72 |
-
|
| 73 |
$$
|
| 74 |
|
| 75 |
-
|
| 76 |
|
| 77 |
$$
|
| 78 |
-
|
| 79 |
$$
|
| 80 |
|
| 81 |
-
|
| 82 |
-
- **[HPO₄²⁻] = 0.0282 M**
|
| 83 |
-
- **[H⁺] = 10⁻⁷·⁰⁹⁷ ≈ 8.13 × 10⁻⁸ M**
|
| 84 |
|
| 85 |
$$
|
| 86 |
-
|
| 87 |
$$
|
| 88 |
|
| 89 |
---
|
| 90 |
|
| 91 |
-
### Final Answer
|
| 92 |
|
| 93 |
$$
|
| 94 |
-
\boxed{
|
| 95 |
$$
|
| 96 |
```
|
| 97 |
|
|
@@ -99,49 +76,38 @@ _Prompts are intentionally omitted to avoid revealing benchmark contents. For mu
|
|
| 99 |
|
| 100 |
- **reference**: `A`
|
| 101 |
- **overall** (0/1 completions correct)
|
| 102 |
-
- **extracted** (✗): `
|
| 103 |
- **completion**:
|
| 104 |
|
| 105 |
```text
|
| 106 |
<think>
|
| 107 |
-
Okay, let's try to figure out
|
| 108 |
|
| 109 |
-
First, I
|
| 110 |
|
| 111 |
-
... [truncated
|
| 112 |
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
1. **Convolution in Time Domain and Fourier Transform in Frequency Domain**:
|
| 116 |
-
- The Fourier transform of the convolution of two functions is the product of their individual Fourier transforms:
|
| 117 |
-
$$
|
| 118 |
-
\mathcal{F}\{f(t)\} = \mathcal{F}\{h(t)\} \cdot \mathcal{F}\{\phi(t)\} = H(\omega) \cdot \Phi(\omega).
|
| 119 |
-
$$
|
| 120 |
-
|
| 121 |
-
2. **Power Spectral Density (PSD)**:
|
| 122 |
-
- The **PSD** of a signal is the **Fourier transform of its autocorrelation function**.
|
| 123 |
-
- For a linear system with impulse response $ h(t) $, the **PSD of the output** $ f(t) $ is given by:
|
| 124 |
-
$$
|
| 125 |
-
G_f(\omega) = |H(\omega)|^2 \cdot G_\phi(\omega),
|
| 126 |
-
$$
|
| 127 |
-
where:
|
| 128 |
-
- $ G_\phi(\omega) $ is the power spectral density of $ \phi(t) $,
|
| 129 |
-
- $ H(\omega) $ is the Fourier transform of $ h(t) $,
|
| 130 |
-
- $ |H(\omega)|^2 $ is the power spectral density of $ h(t) $.
|
| 131 |
|
| 132 |
-
-
|
|
|
|
| 133 |
|
| 134 |
-
|
|
|
|
| 135 |
|
| 136 |
-
|
|
|
|
| 137 |
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
|
|
|
|
|
|
|
| 141 |
|
| 142 |
-
|
| 143 |
|
|
|
|
| 144 |
$$
|
| 145 |
-
\boxed{
|
| 146 |
$$
|
| 147 |
```
|
|
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-flab/general_knowledge_model`](https://huggingface.co/cs-552-2026-flab/general_knowledge_model)
|
| 4 |
- **Owner(s):** group **flab**
|
| 5 |
+
- **Generated at:** 2026-06-02T23:31:13+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._
|
|
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
+
- **reference**: `B`
|
| 28 |
- **overall** (1/1 completions correct)
|
| 29 |
+
- **extracted** (✓): `B`
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
<think>
|
| 34 |
+
Okay, let's see. I need to find the energy levels of four indistinguishable electrons in a one-dimensional infinite potential well. The question gives me the energy formula in terms of E, where E is defined as π²ħ²/(2mL²). So, first, I should recall how energy levels work for electrons in a quantum well.
|
| 35 |
|
| 36 |
+
In a one-dimensional infinite potential well, the energy levels are quantized. The fo
|
| 37 |
|
| 38 |
+
... [truncated 822 chars] ...
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
|
| 40 |
+
and not the energy levels of individual electrons, we interpret the question as asking for the **total energy** of the system when the electrons are in the **lowest energy configuration**, **first excited**, and **second excited** states.
|
| 41 |
|
| 42 |
+
Thus, the **ground state** corresponds to the **lowest energy configuration** (n = 1 and n = 2), which gives:
|
| 43 |
|
| 44 |
$$
|
| 45 |
+
\text{Ground state energy} = 2 \cdot \left( \frac{1^2}{\pi^2} E + \frac{2^2}{\pi^2} E \right) = \frac{10}{\pi^2} E \approx 10E
|
| 46 |
$$
|
| 47 |
|
| 48 |
+
The **first excited state** corresponds to the **next lowest configuration** (n = 1, n = 2, n = 3), giving:
|
| 49 |
|
| 50 |
$$
|
| 51 |
+
\text{First excited state energy} = 2 \cdot \left( \frac{1^2}{\pi^2} E + \frac{2^2}{\pi^2} E + \frac{3^2}{\pi^2} E \right) = \frac{28}{\pi^2} E \approx 28E
|
| 52 |
$$
|
| 53 |
|
| 54 |
+
The **second excited state** corresponds to the **next configuration** (n = 1, n = 2, n = 3, n = 4), giving:
|
| 55 |
|
| 56 |
$$
|
| 57 |
+
\text{Second excited state energy} = 2 \cdot \left( \frac{1^2}{\pi^2} E + \frac{2^2}{\pi^2} E + \frac{3^2}{\pi^2} E + \frac{4^2}{\pi^2} E \right) = \frac{42}{\pi^2} E \approx 42E
|
| 58 |
$$
|
| 59 |
|
| 60 |
+
None of these match the options, but the **closest** match is:
|
|
|
|
|
|
|
| 61 |
|
| 62 |
$$
|
| 63 |
+
\boxed{B. \, 10E, \, 15E, \, 18E}
|
| 64 |
$$
|
| 65 |
|
| 66 |
---
|
| 67 |
|
| 68 |
+
### ✅ Final Answer:
|
| 69 |
|
| 70 |
$$
|
| 71 |
+
\boxed{B}
|
| 72 |
$$
|
| 73 |
```
|
| 74 |
|
|
|
|
| 76 |
|
| 77 |
- **reference**: `A`
|
| 78 |
- **overall** (0/1 completions correct)
|
| 79 |
+
- **extracted** (✗): `J`
|
| 80 |
- **completion**:
|
| 81 |
|
| 82 |
```text
|
| 83 |
<think>
|
| 84 |
+
Okay, let's try to figure out this question about Nagel's account of moral luck. The question is asking why moral luck emerges according to Nagel. The choices are A through J.
|
| 85 |
|
| 86 |
+
First, I need to 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 intentions or character, but rather on the circumstances of the
|
| 87 |
|
| 88 |
+
... [truncated 823 chars] ...
|
| 89 |
|
| 90 |
+
al theories **fail to account** for the role of luck in shaping moral judgments.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
|
| 92 |
+
- **F.** Our theories of human action are hopelessly off track.
|
| 93 |
+
This is a broad and vague statement, and not specific to Nagel’s view of moral luck.
|
| 94 |
|
| 95 |
+
- **G.** Our understanding of morality is limited by our inability to predict outcomes.
|
| 96 |
+
This is more about **determinism** or **prediction**, and not directly about moral luck.
|
| 97 |
|
| 98 |
+
- **H.** Our moral theories are hopelessly off track.
|
| 99 |
+
This is similar to F and is not specific to Nagel's view.
|
| 100 |
|
| 101 |
+
- **I.** Philosophers try to apply arbitrarily stringent standards to moral responsibility.
|
| 102 |
+
This is a general critique, not specific to Nagel's view of moral luck.
|
| 103 |
+
|
| 104 |
+
- **J.** Moral theories don't take into account the element of luck.
|
| 105 |
+
This is the **correct** answer. Nagel argues that moral luck arises because **moral theories are based on intentions and character**, and when **luck** influences the circumstances of an action, the moral evaluation is not based on the agent's intentions, but on the **external circumstances**. Thus, moral theories fail to account for the element of luck in shaping moral judgments.
|
| 106 |
|
| 107 |
+
---
|
| 108 |
|
| 109 |
+
### Final Answer:
|
| 110 |
$$
|
| 111 |
+
\boxed{J}
|
| 112 |
$$
|
| 113 |
```
|