Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
sft
trl
conversational
text-generation-inference
Instructions to use cs-552-2026-bilko/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-bilko/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-bilko/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-bilko/general_knowledge_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-bilko/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-bilko/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-bilko/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-bilko/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-bilko/general_knowledge_model
- SGLang
How to use cs-552-2026-bilko/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-bilko/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-bilko/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-bilko/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-bilko/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-bilko/general_knowledge_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-bilko/general_knowledge_model
Automated MNLP evaluation report (2026-06-11)
#1
by zechen-nlp - opened
- EVAL_REPORT.md +92 -0
EVAL_REPORT.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Automated MNLP evaluation report
|
| 2 |
+
|
| 3 |
+
- **Model repo:** [`cs-552-2026-bilko/general_knowledge_model`](https://huggingface.co/cs-552-2026-bilko/general_knowledge_model)
|
| 4 |
+
- **Owner(s):** group **bilko**
|
| 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:** [`89ea167`](https://huggingface.co/cs-552-2026-bilko/general_knowledge_model/commit/89ea1671e79c98f3aa2d1d5ed7a4f6324bda7aeb)
|
| 13 |
+
- **Message:** Delete lora_adapter
|
| 14 |
+
- **Committed:** 2026-06-06T20:52:59+00:00
|
| 15 |
+
|
| 16 |
+
## Summary
|
| 17 |
+
|
| 18 |
+
| Benchmark | Accuracy | Status |
|
| 19 |
+
|---|---:|---|
|
| 20 |
+
| Math | — | not run |
|
| 21 |
+
| Knowledge | 0.3900 | 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**: `C`
|
| 34 |
+
- **overall** (1/1 completions correct)
|
| 35 |
+
- **extracted** (✓): `C`
|
| 36 |
+
- **completion**:
|
| 37 |
+
|
| 38 |
+
```text
|
| 39 |
+
<think>
|
| 40 |
+
Okay, let's tackle this question. The question is asking which mental disorder has research suggesting a link with acetylcholine. The options are from A to J.
|
| 41 |
+
|
| 42 |
+
First, I need to remember what acetylcholine does. Acetylcholine is a neurotransmitter involved in various bodily functions, including muscle contraction, memory, and learning. It's secreted by the parasympathetic nervous system, wh
|
| 43 |
+
|
| 44 |
+
... [truncated 822 chars] ...
|
| 45 |
+
|
| 46 |
+
opamine dysfunction**, particularly in the prefrontal cortex. Acetylcholine may be involved, but it is not the primary neurotransmitter in this disorder.
|
| 47 |
+
|
| 48 |
+
- **H. Bipolar Disorder**
|
| 49 |
+
Bipolar disorder involves **dopamine and serotonin imbalances**, but there is no strong evidence that acetylcholine plays a central role in its pathophysiology.
|
| 50 |
+
|
| 51 |
+
- **I. Schizophrenia**
|
| 52 |
+
Schizophrenia is associated with **dopamine and serotonin imbalances**, but research on acetylcholine is limited. While cholinergic dysfunction may contribute to some symptoms (e.g., hallucinations), it is not the primary factor.
|
| 53 |
+
|
| 54 |
+
- **J. Major Depressive Disorder**
|
| 55 |
+
Major depression is associated with **serotonin and norepinephrine dysfunction**, not acetylcholine. Acetylcholine is not a primary neurotransmitter in depression.
|
| 56 |
+
|
| 57 |
+
---
|
| 58 |
+
|
| 59 |
+
### Final Conclusion
|
| 60 |
+
|
| 61 |
+
Among all the options, **Alzheimer’s Disease** is most directly associated with **acetylcholine deficits**, which are central to the disease’s progression and clinical features. While **Parkinson’s Disease** also involves acetylcholine, it is primarily associated with **dopamine loss**. Thus, the disorder most clearly linked to acetylcholine is:
|
| 62 |
+
|
| 63 |
+
$$
|
| 64 |
+
\boxed{C}
|
| 65 |
+
$$
|
| 66 |
+
```
|
| 67 |
+
|
| 68 |
+
**Incorrect** (1 shown)
|
| 69 |
+
|
| 70 |
+
- **reference**: `A`
|
| 71 |
+
- **overall** (0/1 completions correct)
|
| 72 |
+
- **extracted** (✗): `<no answer>`
|
| 73 |
+
- **completion**:
|
| 74 |
+
|
| 75 |
+
```text
|
| 76 |
+
<think>
|
| 77 |
+
Okay, let's try to figure out this problem about the power spectral density of a function defined by a convolution. Hmm, so we have f(t) defined as the convolution of h(σ) and φ(t - σ), right? And we need to find the power spectral density of f(t) in terms of the power spectral densities of φ and h, and the Fourier transform of h.
|
| 78 |
+
|
| 79 |
+
First, I remember that the power spectral density (PSD) of
|
| 80 |
+
|
| 81 |
+
... [truncated 822 chars] ...
|
| 82 |
+
|
| 83 |
+
rrelation function. For the convolution, the autocorrelation is the convolution of the autocorrelation functions. So, R_f(τ) = R_h(τ) * R_φ(τ). Then, G_f(ω) = F[R_f(τ)] = F[R_h(τ) * R_φ(τ)] = F(R_h) * F(R_φ) = G_h(ω) * G_φ(ω).
|
| 84 |
+
|
| 85 |
+
But if G_h(ω) is the power spectral density of h(t), then G_f(ω) = G_h(ω) * G_φ(ω). This is the correct relation. Therefore, the answer should be G_f(ω) = G_h(ω) * G_φ(ω). But since G_h(ω) is |H(ω)|², this is |H(ω)|² * G_φ(ω).
|
| 86 |
+
|
| 87 |
+
But none of the choices have this. However, if the question is asking for the power spectral density of f(t) in terms of the Fourier transform of h and the power spectral density of φ, then it might expect us to use the fact that G_f(ω) = G_h(ω) * G_φ(ω), and since G_h(ω) = |H(ω)|², this would be |H(ω)|² * G_φ(ω). But this is not among the choices.
|
| 88 |
+
|
| 89 |
+
Given that, and considering that choice C is G_f(ω) = H(ω) * G_φ(ω)^2, which is |H(ω)|² * G_φ(ω)^2 if H(ω) is real and positive, but this is not generally true.
|
| 90 |
+
|
| 91 |
+
Wait, but if we take the Fourier transform of the convolution, which is H(ω) * H_φ(ω), and then take the magnitude squared, we get |H(ω) * H_φ(ω)|² = |H(ω)|² |H_φ(ω)|² = |H(ω)|² G_φ(ω). This is the same as G_f(ω) = |H(ω)|² G_φ
|
| 92 |
+
```
|