初始化项目，由ModelHub XC社区提供模型

Model: RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf
Source: Original Platform

.gitattributes

@@ -0,0 +1,54 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+astrollama-3-8b-base_aic.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,149 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+astrollama-3-8b-base_aic - GGUF
+- Model creator: https://huggingface.co/AstroMLab/
+- Original model: https://huggingface.co/AstroMLab/astrollama-3-8b-base_aic/
+
+
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [astrollama-3-8b-base_aic.Q2_K.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q2_K.gguf) | Q2_K | 2.96GB |
+| [astrollama-3-8b-base_aic.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
+| [astrollama-3-8b-base_aic.Q3_K.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q3_K.gguf) | Q3_K | 3.74GB |
+| [astrollama-3-8b-base_aic.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
+| [astrollama-3-8b-base_aic.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q3_K_L.gguf) | Q3_K_L | 2.44GB |
+| [astrollama-3-8b-base_aic.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.IQ4_XS.gguf) | IQ4_XS | 3.28GB |
+| [astrollama-3-8b-base_aic.Q4_0.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q4_0.gguf) | Q4_0 | 4.34GB |
+| [astrollama-3-8b-base_aic.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
+| [astrollama-3-8b-base_aic.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
+| [astrollama-3-8b-base_aic.Q4_K.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q4_K.gguf) | Q4_K | 4.58GB |
+| [astrollama-3-8b-base_aic.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
+| [astrollama-3-8b-base_aic.Q4_1.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q4_1.gguf) | Q4_1 | 4.78GB |
+| [astrollama-3-8b-base_aic.Q5_0.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q5_0.gguf) | Q5_0 | 5.21GB |
+| [astrollama-3-8b-base_aic.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
+| [astrollama-3-8b-base_aic.Q5_K.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q5_K.gguf) | Q5_K | 5.34GB |
+| [astrollama-3-8b-base_aic.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
+| [astrollama-3-8b-base_aic.Q5_1.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q5_1.gguf) | Q5_1 | 5.65GB |
+| [astrollama-3-8b-base_aic.Q6_K.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q6_K.gguf) | Q6_K | 6.14GB |
+| [astrollama-3-8b-base_aic.Q8_0.gguf](https://huggingface.co/RichardErkhov/AstroMLab_-_astrollama-3-8b-base_aic-gguf/blob/main/astrollama-3-8b-base_aic.Q8_0.gguf) | Q8_0 | 7.95GB |
+
+
+
+
+Original model description:
+---
+license: mit
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- llama-3
+- astronomy
+- astrophysics
+- arxiv
+inference: false
+base_model:
+- meta-llama/Llama-3-8b-hf
+---
+
+# AstroLLaMA-3-8B-Base_AIC
+
+AstroLLaMA-3-8B is a specialized base language model for astronomy, developed by fine-tuning Meta's LLaMA-3-8b architecture on astronomical literature. This model was developed by the AstroMLab team. It is designed for next token prediction tasks and is not an instruct/chat model.
+
+## Model Details
+
+- **Base Architecture**: LLaMA-3-8b
+- **Training Data**: Abstract, Introduction, and Conclusion (AIC) sections from arXiv's astro-ph category papers
+- **Data Processing**: Optical character recognition (OCR) on PDF files using the Nougat tool, followed by summarization using Qwen-2-8B and LLaMA-3.1-8B.
+- **Fine-tuning Method**: Continual Pre-Training (CPT) using the LMFlow framework
+- **Training Details**:
+  - Learning rate: 2 × 10⁻⁵
+  - Total batch size: 96
+  - Maximum token length: 512
+  - Warmup ratio: 0.03
+  - No gradient accumulation
+  - BF16 format
+  - Cosine decay schedule for learning rate reduction
+  - Training duration: 1 epoch
+- **Primary Use**: Next token prediction for astronomy-related text generation and analysis
+- **Reference**: Pan et al. 2024 [Link to be added]
+
+## Generating text from a prompt
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Load the model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("AstroMLab/astrollama-3-8b-base_aic")
+model = AutoModelForCausalLM.from_pretrained("AstroMLab/astrollama-3-8b-base_aic", device_map="auto")
+
+# Create the pipeline with explicit truncation
+from transformers import pipeline
+generator = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    device_map="auto",
+    truncation=True,
+    max_length=512
+)
+
+# Example prompt from an astronomy paper
+prompt = "In this letter, we report the discovery of the highest redshift, " \
+    "heavily obscured, radio-loud QSO candidate selected using JWST NIRCam/MIRI, " \
+    "mid-IR, sub-mm, and radio imaging in the COSMOS-Web field. "
+
+# Set seed for reproducibility
+torch.manual_seed(42)
+
+# Generate text
+generated_text = generator(prompt, do_sample=True)
+print(generated_text[0]['generated_text'])
+```
+
+## Model Limitations and Biases
+
+A key limitation identified during the development of this model is that training solely on astro-ph data may not be sufficient to significantly improve performance over the base model, especially for the already highly performant LLaMA-3 series. This suggests that to achieve substantial gains, future iterations may need to incorporate a broader range of high-quality astronomical data beyond arXiv, such as textbooks, Wikipedia, and curated summaries.
+
+Here's a performance comparison chart based upon the astronomical benchmarking Q&A as described in [Ting et al. 2024](https://arxiv.org/abs/2407.11194), and Pan et al. 2024:
+
+| Model | Score (%) |
+|-------|-----------|
+| LLaMA-3.1-8B | 73.7 |
+| LLaMA-3-8B | 72.9 |
+| **<span style="color:green">AstroLLaMA-3-8B-Base_AIC (AstroMLab)</span>** | **<span style="color:green">71.9</span>** |
+| Gemma-2-9B | 71.5 |
+| Qwen-2.5-7B | 70.4 |
+| Yi-1.5-9B | 68.4 |
+| InternLM-2.5-7B | 64.5 |
+| Mistral-7B-v0.3 | 63.9 |
+| ChatGLM3-6B | 50.4 |
+| AstroLLaMA-2-7B-AIC | 44.3 |
+| AstroLLaMA-2-7B-Abstract | 43.5 |
+
+As shown, while AstroLLaMA-3-8B performs competitively among models in its class, it does not surpass the performance of the base LLaMA-3-8B model. This underscores the challenges in developing specialized models and the need for more diverse and comprehensive training data.
+
+This model is released primarily for reproducibility purposes, allowing researchers to track the development process and compare different iterations of AstroLLaMA models.
+
+For optimal performance and the most up-to-date capabilities in astronomy-related tasks, we recommend using AstroSage-8B, where these limitations have been addressed. The newer model incorporates expanded training data beyond astro-ph and features a greatly expanded fine-tuning process, resulting in significantly improved performance.
+
+## Ethical Considerations
+
+While this model is designed for scientific use, users should be mindful of potential misuse, such as generating misleading scientific content. Always verify model outputs against peer-reviewed sources for critical applications.
+
+## Citation
+
+If you use this model in your research, please cite:
+
+```
+[Citation for Pan et al. 2024 to be added]
+```
+

astrollama-3-8b-base_aic.IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bfb0ea87025e86d4fc2bb4fd261d426bb42f37765f7475bc2c8daee8ee8301b
+size 4707349056

astrollama-3-8b-base_aic.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f55515bcd9bf338b47c0b308edc6fbd12e1f34dd0fd75d743a06d6e3009275d
+size 3516661760

astrollama-3-8b-base_aic.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:137bf1824913f4a9ecd458a34ed511fc2fee57d5c845f56ecc0c8347bf22c5de
+size 3179131456

astrollama-3-8b-base_aic.Q3_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba5f5804ca04b6fe2411ea4b5b4c512312accd5a8e4584bea1058102d7db66e
+size 4018917952

astrollama-3-8b-base_aic.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34486e63f77e54bde1398b1b7f25f5d33bc0d907278234d993f1bf78e8245c77
+size 2618556416

astrollama-3-8b-base_aic.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba5f5804ca04b6fe2411ea4b5b4c512312accd5a8e4584bea1058102d7db66e
+size 4018917952

astrollama-3-8b-base_aic.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170015236125b19caff4069271f79f432aacdda88a81c30538682a9e339ce4eb
+size 3664499264

astrollama-3-8b-base_aic.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ce961a973d5fa8ca374a7086357fe836bf7a05dcdab67e0163e0cd88ce0264
+size 4661211712

astrollama-3-8b-base_aic.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0486f10ea285e67360eea16136e1c1b7d93c21be180b4e85164215faf60691
+size 5130252864

astrollama-3-8b-base_aic.Q4_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b8dd11b31f12a7ccd20e0a95c3a344cc5fd2cc304576bc8bf6c14e98cfb03f8
+size 4920734272

astrollama-3-8b-base_aic.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b8dd11b31f12a7ccd20e0a95c3a344cc5fd2cc304576bc8bf6c14e98cfb03f8
+size 4920734272

astrollama-3-8b-base_aic.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a87db2239aa4b3e8b408e26f16c6e3b090e8c97054cf74a14f3f1414abf5241
+size 4692668992

astrollama-3-8b-base_aic.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcca1df52f4508147d0de59717e7202b2c7d8777cc645f9aa9ad5a8d7d6426de
+size 5599294016

astrollama-3-8b-base_aic.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70a176b8610d827518f7d99fae0d7813ce6e9914cde54e11af5eeae11d87fbf9
+size 6068335168

astrollama-3-8b-base_aic.Q5_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a6724a6e4d246b3e18dcdbdf56d043d92df40def59270017a06a6e4f66d3db
+size 5732987456

astrollama-3-8b-base_aic.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a6724a6e4d246b3e18dcdbdf56d043d92df40def59270017a06a6e4f66d3db
+size 5732987456

astrollama-3-8b-base_aic.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0eb23968bcc2f345d21ff7ff921e437ed49f1e0248b53ab794370e241a737f
+size 5599294016

astrollama-3-8b-base_aic.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee76d4eb5c03163405ca4f9d40165c975c49b4950ae01527b0909937cd6e18b
+size 6596006464

astrollama-3-8b-base_aic.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aafd8fb4b129333cae274820842e1a571f50cdb8d68da25297bf69a3d06c571
+size 8540770880