Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
trl
sft
conversational
text-generation-inference
Instructions to use cs-552-2026-ChatMODS/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-ChatMODS/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-ChatMODS/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-ChatMODS/general_knowledge_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-ChatMODS/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-ChatMODS/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-ChatMODS/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-ChatMODS/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-ChatMODS/general_knowledge_model
- SGLang
How to use cs-552-2026-ChatMODS/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-ChatMODS/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-ChatMODS/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-ChatMODS/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-ChatMODS/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-ChatMODS/general_knowledge_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-ChatMODS/general_knowledge_model
Update Automated MNLP evaluation report (2026-05-22)
Browse files- EVAL_REPORT.md +12 -87
EVAL_REPORT.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-ChatMODS/general_knowledge_model`](https://huggingface.co/cs-552-2026-ChatMODS/general_knowledge_model)
|
| 4 |
- **Owner(s):** group **ChatMODS**
|
| 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 |
|
|
@@ -24,101 +24,26 @@ _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 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
- **Intermittent incontinence** that is **stress-induced** or **anxiet
|
| 37 |
-
|
| 38 |
-
... [truncated 52 chars] ...
|
| 39 |
-
|
| 40 |
-
triggered by travel** and **resolve after the flight**, indicating a **stressor** (flight) is the trigger.
|
| 41 |
-
- She has **no other significant medical history**, and **oral contraceptive** is the only medication.
|
| 42 |
-
- The **symptoms are not related to physical causes** (no urinary tract infection, structural abnormalities, etc.).
|
| 43 |
-
|
| 44 |
-
### Most Appropriate Next Step:
|
| 45 |
-
The most appropriate next step is to **evaluate the role of stress and anxiety** in her symptoms. Since the symptoms are **stress-related**, the best approach is to **recommend behavioral therapy** or **stress management techniques**.
|
| 46 |
-
|
| 47 |
-
### Correct Answer:
|
| 48 |
-
**C. Recommend behavioral therapy**
|
| 49 |
-
|
| 50 |
-
### Explanation:
|
| 51 |
-
- **Behavioral therapy** (e.g., cognitive-behavioral therapy) is effective for stress-related incontinence.
|
| 52 |
-
- **Avoiding stressful activities** (E) is a **management strategy**, but **not the most appropriate next step** in a clinical setting.
|
| 53 |
-
- **Stopping oral contraceptives** (H) may help, but it is **not the first-line intervention** unless the incontinence is confirmed to be due to hormonal causes.
|
| 54 |
-
- **Psychoanalytic therapy** (I) is **not evidence-based** for this type of incontinence.
|
| 55 |
-
|
| 56 |
-
### Final Answer:
|
| 57 |
-
$$
|
| 58 |
-
\boxed{C}
|
| 59 |
-
$$
|
| 60 |
```
|
| 61 |
|
| 62 |
**Incorrect** (1 shown)
|
| 63 |
|
| 64 |
-
- **reference**: `
|
| 65 |
- **overall** (0/1 completions correct)
|
| 66 |
-
- **extracted** (β): `
|
| 67 |
- **completion**:
|
| 68 |
|
| 69 |
```text
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
\mathcal{L}(y) = -\lambda f \bar{\psi}_f(y) f(y) (\upsilon + X(y)) \psi_f(y)
|
| 74 |
-
$$
|
| 75 |
-
|
| 76 |
-
This is a **vector-like** coupling, and the **boson $ X $** is coupled to **fermions** in a way that depends on the **mass** of the boson, $ m_X = 6 \, \text{GeV} $.
|
| 77 |
-
|
| 78 |
-
---
|
| 79 |
-
|
| 80 |
-
### Step 1: Understand the decay modes
|
| 81 |
-
|
| 82 |
-
The **kinemati
|
| 83 |
-
|
| 84 |
-
... [truncated 823 chars] ...
|
| 85 |
-
|
| 86 |
-
0β5000 MeV
|
| 87 |
-
- **Leptons**: $ e, \mu, \tau $ β masses are in the range of 0.5β100 MeV
|
| 88 |
-
- **Baryons**: $ b, s $ β masses are in the range of 4β100 GeV
|
| 89 |
-
|
| 90 |
-
So, the **boson $ X $** with mass 6 GeV can decay into:
|
| 91 |
-
|
| 92 |
-
- **Fermion pairs** with **total mass less than or equal to 6 GeV**
|
| 93 |
-
|
| 94 |
-
So, the **allowed decay modes** are:
|
| 95 |
-
|
| 96 |
-
- $ X \rightarrow b\bar{b} $ (mass ~4 GeV)
|
| 97 |
-
- $ X \rightarrow s\bar{s} $ (mass ~4 GeV)
|
| 98 |
-
- $ X \rightarrow u\bar{u} $ (mass ~5 GeV)
|
| 99 |
-
- $ X \rightarrow d\bar{d} $ (mass ~5 GeV)
|
| 100 |
-
- $ X \rightarrow \tau^+ \tau^- $ (mass ~2000 MeV)
|
| 101 |
-
- $ X \rightarrow \mu^+ \mu^- $ (mass ~200 MeV)
|
| 102 |
-
- $ X \rightarrow e^+ e^- $ (mass ~100 MeV)
|
| 103 |
-
|
| 104 |
-
---
|
| 105 |
-
|
| 106 |
-
### Step 4: Choose the correct option
|
| 107 |
-
|
| 108 |
-
From the choices:
|
| 109 |
-
|
| 110 |
-
- **A** includes $ b\bar{b}, s\bar{s}, u\bar{u}, d\bar{d}, \tau^+ \tau^-, \mu^+ \mu^-, e^+ e^- $
|
| 111 |
-
- **B** includes $ c\bar{c}, s\bar{s}, u\bar{u}, d\bar{d}, \tau^+ \tau^-, \mu^+ \mu^-, e^+ e^- $
|
| 112 |
-
- **C** includes $ c\bar{c}, s\bar{s}, u\bar{u}, d\bar{d}, t\bar{t}, \tau^+ \tau^-, \mu^+ \mu^-, e^+ e^- $
|
| 113 |
-
- **D** includes $ b\bar{b}, s\bar{s}, u\bar{u}, d\bar{d}, \tau^+ \tau^-, e^+ e^- $
|
| 114 |
-
|
| 115 |
-
Only **A** includes all **allowed decay modes** of $ X $ with mass 6 GeV.
|
| 116 |
-
|
| 117 |
-
---
|
| 118 |
-
|
| 119 |
-
### β
Final Answer:
|
| 120 |
-
|
| 121 |
-
$$
|
| 122 |
-
\boxed{\text{A}}
|
| 123 |
-
$$
|
| 124 |
```
|
|
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-ChatMODS/general_knowledge_model`](https://huggingface.co/cs-552-2026-ChatMODS/general_knowledge_model)
|
| 4 |
- **Owner(s):** group **ChatMODS**
|
| 5 |
+
- **Generated at:** 2026-05-22T03:04:12+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 | 0.2800 | ok |
|
| 16 |
| Multilingual | β | not run |
|
| 17 |
| Safety | β | not run |
|
| 18 |
|
|
|
|
| 24 |
|
| 25 |
**Correct** (1 shown)
|
| 26 |
|
| 27 |
+
- **reference**: `A`
|
| 28 |
- **overall** (1/1 completions correct)
|
| 29 |
+
- **extracted** (β): `A`
|
| 30 |
- **completion**:
|
| 31 |
|
| 32 |
```text
|
| 33 |
+
Let me analyze each option:
|
| 34 |
+
The correct answer is A. No, the school exercised its appropriate function of trying to restrict the use of vulgarity and offensive discourse in a high school setting where free speech may be limited..
|
| 35 |
+
\boxed{A}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
```
|
| 37 |
|
| 38 |
**Incorrect** (1 shown)
|
| 39 |
|
| 40 |
+
- **reference**: `A`
|
| 41 |
- **overall** (0/1 completions correct)
|
| 42 |
+
- **extracted** (β): `B`
|
| 43 |
- **completion**:
|
| 44 |
|
| 45 |
```text
|
| 46 |
+
Let me analyze each option:
|
| 47 |
+
The correct answer is B.
|
| 48 |
+
\boxed{B}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
```
|