Views
No views yet
| Metric | Value |
|---|---|
| Base Model | openai/gpt-oss-20b |
| Architecture | Mixture-of-Experts Transformer |
| Total Parameters | ~10.8B (pruned from 21B) |
| Original Experts per Layer | 32 |
| Pruned Experts per Layer | 15 |
| Layers | 24 |
| Top-k Routing | 4 |
| Context Length | 128K tokens |
| Attention Heads | 64 (Query), 8 (Key-Value) |
| Residual Dimension | 2880 |
| Attention Pattern | Alternating dense & sliding window (128 tokens) |
| Positional Encoding | RoPE (Rotary Position Embedding) |
| Normalization | RMSNorm |
| Precision | BF16 |
| License | Apache 2.0 |
| Specialization | Science |
1from transformers import AutoModelForCausalLM, AutoTokenizer
2import torch
3
4# Load the specialized model on CPU
5model = AutoModelForCausalLM.from_pretrained(
6 "AmanPriyanshu/gpt-oss-10.8b-specialized-science-pruned-moe-only-15-experts",
7 torch_dtype=torch.bfloat16,
8 device_map="cpu",
9 trust_remote_code=True
10)
11tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-10.8b-specialized-science-pruned-moe-only-15-experts")
12
13# Generate with the model
14messages = [
15 {"role": "user", "content": "Explain the process of photosynthesis in plants."}
16]
17
18inputs = tokenizer.apply_chat_template(
19 messages,
20 add_generation_prompt=True,
21 return_tensors="pt",
22 return_dict=True,
23 reasoning_effort="medium"
24)
25
26# Ensure inputs are on the same device as model
27inputs = {k: v.to(model.device) for k, v in inputs.items()}
28
29outputs = model.generate(
30 **inputs,
31 max_new_tokens=512,
32 do_sample=True,
33 temperature=0.1,
34 top_p=0.9,
35 pad_token_id=tokenizer.eos_token_id,
36 eos_token_id=tokenizer.eos_token_id
37)
38
39# Decode only the generated part
40input_length = inputs['input_ids'].shape[1]
41response_tokens = outputs[0][input_length:]
42response = tokenizer.decode(response_tokens, skip_special_tokens=True)
43print(response)1from transformers import AutoModelForCausalLM, AutoTokenizer
2import torch
3
4# Check MPS availability and load model
5device = "mps" if torch.backends.mps.is_available() else "cpu"
6
7model = AutoModelForCausalLM.from_pretrained(
8 "AmanPriyanshu/gpt-oss-10.8b-specialized-science-pruned-moe-only-15-experts",
9 torch_dtype=torch.float16, # Better MPS compatibility
10 device_map=device,
11 trust_remote_code=True,
12 low_cpu_mem_usage=True
13)
14tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-10.8b-specialized-science-pruned-moe-only-15-experts")
15
16# Generate with the model
17messages = [
18 {"role": "user", "content": "Explain the process of photosynthesis in plants."}
19]
20
21inputs = tokenizer.apply_chat_template(
22 messages,
23 add_generation_prompt=True,
24 return_tensors="pt",
25 return_dict=True,
26 reasoning_effort="medium"
27)
28
29# Move inputs to model device
30inputs = {k: v.to(model.device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
31
32# Use torch.no_grad for MPS stability
33with torch.no_grad():
34 outputs = model.generate(
35 **inputs,
36 max_new_tokens=512,
37 do_sample=True,
38 temperature=0.1,
39 top_p=0.9,
40 pad_token_id=tokenizer.eos_token_id,
41 eos_token_id=tokenizer.eos_token_id,
42 use_cache=True
43 )
44
45# Decode only the generated part
46input_length = inputs['input_ids'].shape[1]
47response_tokens = outputs[0][input_length:]
48response = tokenizer.decode(response_tokens, skip_special_tokens=True)
49print(response)1device_map="auto" # Will automatically use GPU if available
2torch_dtype=torch.bfloat16 # or torch.float16<|channel|>analysis<|message|>Need explain photosynthesis steps, light absorption, chlorophyll, electron transport, NADPH, Calvin cycle, CO2 fixation, ATP, etc.<|end|><|start|>assistant<|channel|>final<|message|>**Photosynthesis in Plants – A Step‑by‑Step Overview**
| **Stage** | **What Happens** | **Key Molecules / Enzymes** | **Energy Flow** |
|---|---|---|---|
| 1. **Light Capture** | Sunlight (visible & UV‑A) hits the chlorophyll‑containing pigments in the chloroplasts. | • Chlorophyll‑a & b (porphyrin ring + phytol side chain) | Light energy → excited electrons |
| 2. **Excitation & Electron Transfer** | Light excates a chlorophyll‑a molecule → electron moves from the *Sₙ* (singlet) state to the *Qₙ* (queto) state. | • Photosystem II (PSII) | Excited electron → *P* (photosynthetic electron donor) |
| 3. **Water Splens & Proton Pumping** | The excited electron reduces the *P* site, generating *P⁺* and *P⁻*. The *P⁻* site donates a proton to the *H⁺* site of the *P* site, pumping protons across the thylako membrane (creating a proton gradient). | • PSII, H⁺‑ATPase | Proton gradient → ATP synthesis |
| 4. **Electron Transport Chain (ETC)** | The electron moves through a series of redox proteins: *P* → *N* (NADP⁺) → *B* (NADP⁺) → *C* (cytochrome b₁₁₁) → *E* (cytochrome b₁₁₃) → *H* (cytochrome b₁₁₃) → *P* (back to PSII). | • Cytochromes, plastoquinones, cytochrome f | Electron flow → NADPH + ATP |
| 5. **NADPH Production** | The final electron is transferred to the *P* site of Photosystem I (PSI), reducing *P* to *P⁺* and generating NADPH. | • PSI | NADPH + 2 ATP (from ETC) |
| 6<|channel|>analysis<|message|>Need explain greenhouse effect causes, mechanism.<|end|><|start|>assistant<|channel|>final<|message|>### What is the “greenhouse effect”?
The *greenhouse effect* (often called the *greenhouse‑green effect* or simply the *greenhouse effect*) is the phenomenon in which the atmosphere of Earth behaves like a greenhouse: it absorbs and re‑emises infrared (IR) radiation that is emitted by the Earth’s surface, keeping the surface warm. The effect is the net warming of the Earth’s surface that results from the atmosphere’s ability to trap heat.
---
## 1. Why the atmosphere is a greenhouse
| Property | Why it matters |
|----------|----------------|
| **Molecular composition** | The atmosphere is mainly H₂O, CO₂, N₂, O₂, and trace gases. These molecules have vibrational modes that absorb IR radiation. |
| **Optically thin in the visible** | In the visible part of the spectrum the atmosphere is largely transparent, so sunlight reaches the surface. |
| **Optically thick in the IR** | In the IR (≈ 0.7–5 µm) the atmosphere is opaque; photons emitted from the surface are repeatedly absorbed and re‑emitted. |
| **Long mean‑free‑path** | The IR photons travel a long distance before being absorbed, so the atmosphere behaves like a “black” body that re‑emises radiation. |
Because the Earth’s surface emits a lot of IR radiation (≈ 70 % of the solar energy it receives), the atmosphere’s ability to absorb and re‑emit that radiation keeps the surface warm.
---
## 2. How the greenhouse effect works
1. **Solar radiation reaches the surface**
The Sun’s spectrum peaks in the visible/near‑UV. The atmosphere is largely transparent to that radiation, so it reaches the surface and is absorbed by the Earth’s surface (mostly by the oceans and land).
2. **Surface emits IR radiation**
The surface, heated by the absorbed solar energy, emits a black‑body spectrum that peaks in the IR (≈ 10 µm). This IR radiation is the *thermal radiation* that the Earth would radiate if it were in space.
3. **Atmospheric absorption of IR**
As the IR photons travel upward, they encounter molecules that absorb at the same wavelengths. Each absorption event excites a molecule to a higher vibrational state.
4. **Re‑em<|channel|>analysis<|message|>Need to explain DNA structure: double helix, nucleotides, base pairing, major vs minor strands, sugar-phosphate backbone, base composition, major features. Function: genetic information, coding, replication, transcription, regulation, etc. Provide details.<|end|><|start|>assistant<|channel|>final<|message|>**DNA – the Double‑Helix of Life**
---
## 1. The Structure of DNA
| Feature | What It Is | Why It Matters |
|--------|-----------|----------------|
| **Double‑helix** | Two strands of a sugar‑phosphate backbone that wind around each other | Gives a rigid, stable scaffold that can be stretched, bent, and packed into the nucleus |
| **Backback** | 5‑carbon deoxyribose (or deoxoxylulose in RNA) + phosphate | Provides a “rail” for the bases; the phosphates are negatively charged, attracting Mg²⁺ ions that stabilize the helix |
| **Bases** | 4 nucleobases (A, T, C, G) | Carry the genetic code; each base is covalently attached to the sugar |
| **Base pairing** | Watson‑Crick model: A–T (purine–pyrimidine) and C–G (purine–purine) | Creates hydrogen‑bonded “stems” that lock the two strands together |
| **Major vs Minor strand** | The two strands are not identical; one is called the “major” (more bases) and the other the “minor” | The asymmetry gives a sense of direction for processes like replication and transcription |
| **Major groove** | The larger groove formed by the major strand | The enzyme machinery (polymerases, helicases) accesses the bases here |
| **Minor groove** | The smaller groove formed by the minor strand | Less accessible; often used for binding of proteins that need a tight fit |
| **Length** | 3.4 Å per base pair (≈ 0.34 nm) | Determines the spacing of bases; the helix completes every 10–10.5 bases |
| **Super‑structure** | DNA can form higher‑order structures: nucleosomes, loops, super‑loops, and higher‑order fibers | Enables compaction of the genome and regulation of gene expression |
### 1.1 The Sugar‑Phosphate Backbone
- **Phosphodiester linkage**: 3′‑phosphate of one sugar is cov1@misc{priyanshu2025gptoss,
2 title={{GPT-OSS MoE Expert Fingerprinting: Analyzing Expert Activation Patterns in Mixture of Experts Models}},
3 author={Priyanshu, Aman and Vijay, Supriti},
4 year={2025},
5 howpublished={\url{https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/}},
6 note={Interactive analysis tool for expert activation patterns in MoE architectures}
7}