Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
grpo
trl
conversational
text-generation-inference
Instructions to use cs-552-2026-MMRF/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-MMRF/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-MMRF/general_knowledge_model") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("cs-552-2026-MMRF/general_knowledge_model") model = AutoModelForCausalLM.from_pretrained("cs-552-2026-MMRF/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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use cs-552-2026-MMRF/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-MMRF/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-MMRF/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cs-552-2026-MMRF/general_knowledge_model
- SGLang
How to use cs-552-2026-MMRF/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-MMRF/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-MMRF/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-MMRF/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-MMRF/general_knowledge_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cs-552-2026-MMRF/general_knowledge_model with Docker Model Runner:
docker model run hf.co/cs-552-2026-MMRF/general_knowledge_model
Update Automated MNLP evaluation report (2026-06-04)
Browse files- EVAL_REPORT.md +78 -9
EVAL_REPORT.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-MMRF/general_knowledge_model`](https://huggingface.co/cs-552-2026-MMRF/general_knowledge_model)
|
| 4 |
- **Owner(s):** group **MMRF**
|
| 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._
|
|
@@ -12,7 +12,7 @@ _This PR is opened automatically by the course CI. It is **non-blocking** — yo
|
|
| 12 |
| Benchmark | Accuracy | Status |
|
| 13 |
|---|---:|---|
|
| 14 |
| Math | — | not run |
|
| 15 |
-
| Knowledge | 0.
|
| 16 |
| Multilingual | — | not run |
|
| 17 |
| Safety | — | not run |
|
| 18 |
|
|
@@ -24,30 +24,99 @@ _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 |
|
|
|
|
|
|
|
|
|
|
| 35 |
</think>
|
| 36 |
|
| 37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
```
|
| 39 |
|
| 40 |
**Incorrect** (1 shown)
|
| 41 |
|
| 42 |
-
- **reference**: `
|
| 43 |
- **overall** (0/1 completions correct)
|
| 44 |
-
- **extracted** (✗): `
|
| 45 |
- **completion**:
|
| 46 |
|
| 47 |
```text
|
| 48 |
<think>
|
|
|
|
| 49 |
|
| 50 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
-
|
|
|
|
|
|
|
| 53 |
```
|
|
|
|
| 2 |
|
| 3 |
- **Model repo:** [`cs-552-2026-MMRF/general_knowledge_model`](https://huggingface.co/cs-552-2026-MMRF/general_knowledge_model)
|
| 4 |
- **Owner(s):** group **MMRF**
|
| 5 |
+
- **Generated at:** 2026-06-04T22:19:52+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._
|
|
|
|
| 12 |
| Benchmark | Accuracy | Status |
|
| 13 |
|---|---:|---|
|
| 14 |
| Math | — | not run |
|
| 15 |
+
| Knowledge | 0.2400 | ok |
|
| 16 |
| Multilingual | — | not run |
|
| 17 |
| Safety | — | not run |
|
| 18 |
|
|
|
|
| 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 try to figure out which investment Mr. James should choose between corporate and municipal bonds. So, he's in the 50% income tax bracket. The corporate bonds pay 8% interest, and the municipal bonds pay 4.5%.
|
| 35 |
+
|
| 36 |
+
First, I remember that municipal bonds are tax-exempt, right? So if he invests in them, the interest he earns wouldn't be taxed at all. But corporate bonds are taxed at
|
| 37 |
+
|
| 38 |
+
... [truncated 482 chars] ...
|
| 39 |
+
|
| 40 |
+
the same as the municipal bond's 4.5% after tax? Wait, no, maybe I need to calculate it more carefully.
|
| 41 |
|
| 42 |
+
Let me do the math. For corporate bonds: 8% interest, but taxed at 50%. So his net gain would be 8% * (1 - 0.5) = 4%. For municipal bonds: 4.5% interest, which is tax-free. So his net gain is 4.5%. Therefore, the municipal bonds would give him a higher return after taxes. So even though the municipal bonds have a lower interest rate, they are tax-free, so they're better for him.
|
| 43 |
+
|
| 44 |
+
Therefore, the answer would be municipal bonds. Let me check the choices again. The options are B. municipal bonds. Yes, that's the one. So the correct choice is B.
|
| 45 |
</think>
|
| 46 |
|
| 47 |
+
Mr. James is in the 50% income tax bracket and has the option to invest in corporate or municipal bonds.
|
| 48 |
+
|
| 49 |
+
- **Corporate bonds** pay 8% interest, but this interest is fully taxable at 50%. His net return would be:
|
| 50 |
+
$$
|
| 51 |
+
8\% \times (1 - 0.50) = 4\%.
|
| 52 |
+
$$
|
| 53 |
+
|
| 54 |
+
- **Municipal bonds** pay 4.5% interest, which is tax-exempt. Thus, his net return would be:
|
| 55 |
+
$$
|
| 56 |
+
4.5\% \text{ (tax-free)}.
|
| 57 |
+
$$
|
| 58 |
+
|
| 59 |
+
Since the municipal bonds yield a higher return after taxes (4.5% vs. 4%), **municipal bonds are wiser** for Mr. James.
|
| 60 |
+
|
| 61 |
+
**Answer:** $\boxed{B}$
|
| 62 |
```
|
| 63 |
|
| 64 |
**Incorrect** (1 shown)
|
| 65 |
|
| 66 |
+
- **reference**: `C`
|
| 67 |
- **overall** (0/1 completions correct)
|
| 68 |
+
- **extracted** (✗): `\text{A. Sieder and Tate's formula: 60.73 Btu/hr-ft}^2-^\circ\text{F}, \text{Hausen's formula: 52.66 Btu/hr-ft}^2-^\circ...`
|
| 69 |
- **completion**:
|
| 70 |
|
| 71 |
```text
|
| 72 |
<think>
|
| 73 |
+
Okay, let's try to figure out this heat transfer problem. So, we have water flowing through a pipe, and we need to find the heat transfer coefficient using Sieder and Tate's formula and Hausen's formula. The given data is the flow rate, pipe diameter, length, inlet and outlet temperatures, and the assumption that the flow is laminar.
|
| 74 |
|
| 75 |
+
First, let me recall what these formulas are. Sieder a
|
| 76 |
+
|
| 77 |
+
... [truncated 823 chars] ...
|
| 78 |
+
|
| 79 |
+
\text{Pr} = \frac{\nu}{\alpha} = \frac{1.73 \times 10^{-7}}{0.000012} \approx 0.144
|
| 80 |
+
$$
|
| 81 |
+
|
| 82 |
+
---
|
| 83 |
+
|
| 84 |
+
### **Step 4: Apply Sieder and Tate’s Formula**
|
| 85 |
+
|
| 86 |
+
$$
|
| 87 |
+
\text{Nu} = 0.023 \cdot \text{Re}^{1/4} \cdot \text{Pr}^{1/3} \cdot \left(1 + 0.037 \cdot \text{Re}^{1/2} / \text{Pr}^{1/3}\right)^{1/4}
|
| 88 |
+
$$
|
| 89 |
+
|
| 90 |
+
- $ \text{Re}^{1/4} \approx 15 $
|
| 91 |
+
- $ \text{Pr}^{1/3} \approx 0.52 $
|
| 92 |
+
- $ \text{Re}^{1/2} \approx 229.75 $
|
| 93 |
+
- $ 0.037 \cdot \text{Re}^{1/2} / \text{Pr}^{1/3} \approx 16.37 $
|
| 94 |
+
- $ 1 + 16.37 = 17.37 $
|
| 95 |
+
- $ \text{Nu} \approx 0.023 \cdot 15 \cdot 0.52 \cdot 2.04 \approx 0.365 $
|
| 96 |
+
|
| 97 |
+
---
|
| 98 |
+
|
| 99 |
+
### **Step 5: Calculate the Heat Transfer Coefficient**
|
| 100 |
+
|
| 101 |
+
$$
|
| 102 |
+
h = \frac{\text{Nu} \cdot k}{L} = \frac{0.365 \cdot 0.124}{0.0492} \approx 0.919 \, \text{Btu}/\text{hr} \cdot \text{ft}^2 \cdot ^\circ\text{F}
|
| 103 |
+
$$
|
| 104 |
+
|
| 105 |
+
---
|
| 106 |
+
|
| 107 |
+
### **Step 6: Apply Hausen’s Formula**
|
| 108 |
+
|
| 109 |
+
Hausen’s formula is identical to Sieder and Tate’s for laminar flow in a circular pipe. Therefore, the result remains the same:
|
| 110 |
+
|
| 111 |
+
$$
|
| 112 |
+
h \approx 0.919 \, \text{Btu}/\text{hr} \cdot \text{ft}^2 \cdot ^\circ\text{F}
|
| 113 |
+
$$
|
| 114 |
+
|
| 115 |
+
---
|
| 116 |
+
|
| 117 |
+
### **Final Answer:**
|
| 118 |
|
| 119 |
+
$$
|
| 120 |
+
\boxed{\text{A. Sieder and Tate's formula: 60.73 Btu/hr-ft}^2-^\circ\text{F}, \text{Hausen's formula: 52.66 Btu/hr-ft}^2-^\circ\text{F}}
|
| 121 |
+
$$
|
| 122 |
```
|