richarderkhov/josephgflowers_-_qllama-.5b-rag-1-gguf overview
Quantization made by Richard Erkhov. Github Discord Request more models Qllama-.5B-RAG-1 - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | Qllama-.5B-RAG-1.Q2K.gguf | Q2K | 0.23GB | | Qllama-.5B-RAG-1.IQ3XS.gguf | IQ3XS | 0.24GB | | Qllama-.5B-RAG-1.IQ3S.gguf | IQ3S | 0.25GB | | Qllama-.5B-RAG-1.Q3KS.gguf | Q3KS | 0.25GB | | Qllama-.5B-RAG-1.IQ3M.gguf | IQ3M | 0.26GB | | Qllama-.5B-RAG-1.Q3K.gguf | Q3K | 0.26GB | | Qllama-.5B-RAG-1.Q3KM.gguf | Q3KM | 0.26GB | | Qllama-.5B-RAG-1.Q3KL.gguf | Q3KL | 0.28GB | | Qllama-.5B-RAG-1.IQ4XS.gguf | IQ4XS | 0.28GB | | Qllama-.5B-RAG-1.Q40.gguf | Q40 | 0.29GB | | Qllama-.5B-RAG-1.IQ4NL.gguf | IQ4NL | 0.29GB | | Qllama-.5B-RAG-1.Q4KS.gguf | Q4KS | 0.29GB | | Qllama-.5B-RAG-1.Q4K.gguf | Q4K | 0.3GB | | Qllama-.5B-RAG-1.Q4KM.gguf | Q4KM | 0.3GB | | Qllama-.5B-RAG-1.Q41.gguf | Q41 | 0.3GB | | Qllama-.5B-RAG-1.Q50.gguf | Q50 | 0.32GB | | Qllama-.5B-RAG-1.Q5KS.gguf | Q5KS | 0.32GB | | Qllama-.5B-RAG-1.Q5K.gguf | Q5K | 0.33GB | | Qllama-.5B-RAG-1.Q5KM.gguf | Q5KM | 0.33GB | | Qllama-.5B-RAG-1.Q51.gguf | Q51 | 0.34GB | | Qllama-.5B-RAG-1.Q6K.gguf | Q6K | 0.36GB | | Qllama-.5B-RAG-1.Q80.gguf | Q80 | 0.47GB | Original model description: --- license: mit --- This model needs further fine tuning. See: txtai-rag.py for rag implimentation with txt ai wikipedia. Llamafyd version of Qwen .5B further fine tuned 1 epoch on wiki, math, science, and chat datasets. Based on Cinder data. This model further fine tuned 1 epoch on rag data. Rough list of final datasets: formattedbeaugogh-openorca-multiplechoice-10k.txt formattedBYC-Sophie-samsum-chatgpt-summary.txt formattedconversationbio.txt formattedconversationcreatecinder1.txt formattedconversationElectrical-engineering.txt formattedconversationmultiturnstem.txt formattedconversationphysics.txt formattedconversationqaragchemprogdataset.txt formattedconversationqarobotaidataset.txt formattedconversationqashopifydataset1rag.txt formattedconversationqashopifydatasetrag.txt formatteddyumat-databricks-dolly-5k-rag-split.txt formattedHypoxiic-wikipedia-summary-subset1k-summarytoken.txt formattedneural-bridge-rag-dataset-12000.txt formattedrachid16-ragfinetuningdata.txt formattedtinystories1summarytokentagtoken-xaa.txt formattedtinystories2summarytokenassistant-xah.txt medragsmall.txt zformattedcinder_test.txt
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qllama-.5B-RAG-1.IQ3_M.gguf | GGUF | IQ3_M | 261.75 MB | Download |
| Qllama-.5B-RAG-1.IQ3_S.gguf | GGUF | IQ3_S | 254.28 MB | Download |
| Qllama-.5B-RAG-1.IQ3_XS.gguf | GGUF | IQ3_XS | 247.39 MB | Download |
| Qllama-.5B-RAG-1.IQ4_NL.gguf | GGUF | IQ4_NL | 294.36 MB | Download |
| Qllama-.5B-RAG-1.IQ4_XS.gguf | GGUF | IQ4_XS | 285.43 MB | Download |
| Qllama-.5B-RAG-1.Q2_K.gguf | GGUF | Q2_K | 236.00 MB | Download |
| Qllama-.5B-RAG-1.Q3_K.gguf | GGUF | Q3_K | 270.01 MB | Download |
| Qllama-.5B-RAG-1.Q3_K_L.gguf | GGUF | Q3_K_L | 283.67 MB | Download |
| Qllama-.5B-RAG-1.Q3_K_M.gguf | GGUF | Q3_K_M | 270.01 MB | Download |
| Qllama-.5B-RAG-1.Q3_K_S.gguf | GGUF | Q3_K_S | 254.28 MB | Download |
| Qllama-.5B-RAG-1.Q4_0.gguf | GGUF | — | 293.33 MB | Download |
| Qllama-.5B-RAG-1.Q4_1.gguf | GGUF | — | 311.70 MB | Download |
| Qllama-.5B-RAG-1.Q4_K.gguf | GGUF | Q4_K | 304.93 MB | Download |
| Qllama-.5B-RAG-1.Q4_K_M.gguf | GGUF | Q4_K_M | 304.93 MB | Download |
| Qllama-.5B-RAG-1.Q4_K_S.gguf | GGUF | Q4_K_S | 294.86 MB | Download |
| Qllama-.5B-RAG-1.Q5_0.gguf | GGUF | — | 330.08 MB | Download |
| Qllama-.5B-RAG-1.Q5_1.gguf | GGUF | — | 348.45 MB | Download |
| Qllama-.5B-RAG-1.Q5_K.gguf | GGUF | Q5_K | 336.05 MB | Download |
| Qllama-.5B-RAG-1.Q5_K_M.gguf | GGUF | Q5_K_M | 336.05 MB | Download |
| Qllama-.5B-RAG-1.Q5_K_S.gguf | GGUF | Q5_K_S | 330.08 MB | Download |
| Qllama-.5B-RAG-1.Q6_K.gguf | GGUF | Q6_K | 369.12 MB | Download |
| Qllama-.5B-RAG-1.Q8_0.gguf | GGUF | — | 476.26 MB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"frontmatter": {},
"hero_image_url": "",
"summary": "Quantization made by Richard Erkhov. Github Discord Request more models Qllama-.5B-RAG-1 - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | Qllama-.5B-RAG-1.Q2_K.gguf | Q2_K | 0.23GB | | Qllama-.5B-RAG-1.IQ3_XS.gguf | IQ3_XS | 0.24GB | | Qllama-.5B-RAG-1.IQ3_S.gguf | IQ3_S | 0.25GB | | Qllama-.5B-RAG-1.Q3_K_S.gguf | Q3_K_S | 0.25GB | | Qllama-.5B-RAG-1.IQ3_M.gguf | IQ3_M | 0.26GB | | Qllama-.5B-RAG-1.Q3_K.gguf | Q3_K | 0.26GB | | Qllama-.5B-RAG-1.Q3_K_M.gguf | Q3_K_M | 0.26GB | | Qllama-.5B-RAG-1.Q3_K_L.gguf | Q3_K_L | 0.28GB | | Qllama-.5B-RAG-1.IQ4_XS.gguf | IQ4_XS | 0.28GB | | Qllama-.5B-RAG-1.Q4_0.gguf | Q4_0 | 0.29GB | | Qllama-.5B-RAG-1.IQ4_NL.gguf | IQ4_NL | 0.29GB | | Qllama-.5B-RAG-1.Q4_K_S.gguf | Q4_K_S | 0.29GB | | Qllama-.5B-RAG-1.Q4_K.gguf | Q4_K | 0.3GB | | Qllama-.5B-RAG-1.Q4_K_M.gguf | Q4_K_M | 0.3GB | | Qllama-.5B-RAG-1.Q4_1.gguf | Q4_1 | 0.3GB | | Qllama-.5B-RAG-1.Q5_0.gguf | Q5_0 | 0.32GB | | Qllama-.5B-RAG-1.Q5_K_S.gguf | Q5_K_S | 0.32GB | | Qllama-.5B-RAG-1.Q5_K.gguf | Q5_K | 0.33GB | | Qllama-.5B-RAG-1.Q5_K_M.gguf | Q5_K_M | 0.33GB | | Qllama-.5B-RAG-1.Q5_1.gguf | Q5_1 | 0.34GB | | Qllama-.5B-RAG-1.Q6_K.gguf | Q6_K | 0.36GB | | Qllama-.5B-RAG-1.Q8_0.gguf | Q8_0 | 0.47GB | Original model description: --- license: mit --- This model needs further fine tuning. See: txtai-rag.py for rag implimentation with txt ai wikipedia. Llamafyd version of Qwen .5B further fine tuned 1 epoch on wiki, math, science, and chat datasets. Based on Cinder data. This model further fine tuned 1 epoch on rag data. Rough list of final datasets: formatted_beaugogh-openorca-multiplechoice-10k.txt formatted_BYC-Sophie-samsum-chatgpt-summary.txt formatted_conversation_bio.txt formatted_conversation_create_cinder_1.txt formatted_conversation_Electrical-engineering.txt formatted_conversation_multiturn_stem.txt formatted_conversation_physics.txt formatted_conversation_qa_rag_chem_prog_dataset.txt formatted_conversation_qa_robot_ai_dataset.txt formatted_conversation_qa_shopify_dataset1_rag.txt formatted_conversation_qa_shopify_dataset_rag.txt formatted_dyumat-databricks-dolly-5k-rag-split.txt formatted_Hypoxiic-wikipedia-summary-subset1k-summary_token.txt formatted_neural-bridge-rag-dataset-12000.txt formatted_rachid16-rag_finetuning_data.txt formatted_tiny_stories_1_summary_token_tag_token-xaa.txt formatted_tiny_stories_2_summary_token_assistant-xah.txt med_rag_small.txt z_formatted_cinder_test.txt",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nQllama-.5B-RAG-1 - GGUF\n- Model creator: https://huggingface.co/Josephgflowers/\n- Original model: https://huggingface.co/Josephgflowers/Qllama-.5B-RAG-1/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Qllama-.5B-RAG-1.Q2_K.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q2_K.gguf) | Q2_K | 0.23GB |\n| [Qllama-.5B-RAG-1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.IQ3_XS.gguf) | IQ3_XS | 0.24GB |\n| [Qllama-.5B-RAG-1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.IQ3_S.gguf) | IQ3_S | 0.25GB |\n| [Qllama-.5B-RAG-1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q3_K_S.gguf) | Q3_K_S | 0.25GB |\n| [Qllama-.5B-RAG-1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.IQ3_M.gguf) | IQ3_M | 0.26GB |\n| [Qllama-.5B-RAG-1.Q3_K.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q3_K.gguf) | Q3_K | 0.26GB |\n| [Qllama-.5B-RAG-1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q3_K_M.gguf) | Q3_K_M | 0.26GB |\n| [Qllama-.5B-RAG-1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q3_K_L.gguf) | Q3_K_L | 0.28GB |\n| [Qllama-.5B-RAG-1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.IQ4_XS.gguf) | IQ4_XS | 0.28GB |\n| [Qllama-.5B-RAG-1.Q4_0.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q4_0.gguf) | Q4_0 | 0.29GB |\n| [Qllama-.5B-RAG-1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.IQ4_NL.gguf) | IQ4_NL | 0.29GB |\n| [Qllama-.5B-RAG-1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q4_K_S.gguf) | Q4_K_S | 0.29GB |\n| [Qllama-.5B-RAG-1.Q4_K.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q4_K.gguf) | Q4_K | 0.3GB |\n| [Qllama-.5B-RAG-1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q4_K_M.gguf) | Q4_K_M | 0.3GB |\n| [Qllama-.5B-RAG-1.Q4_1.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q4_1.gguf) | Q4_1 | 0.3GB |\n| [Qllama-.5B-RAG-1.Q5_0.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q5_0.gguf) | Q5_0 | 0.32GB |\n| [Qllama-.5B-RAG-1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q5_K_S.gguf) | Q5_K_S | 0.32GB |\n| [Qllama-.5B-RAG-1.Q5_K.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q5_K.gguf) | Q5_K | 0.33GB |\n| [Qllama-.5B-RAG-1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q5_K_M.gguf) | Q5_K_M | 0.33GB |\n| [Qllama-.5B-RAG-1.Q5_1.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q5_1.gguf) | Q5_1 | 0.34GB |\n| [Qllama-.5B-RAG-1.Q6_K.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q6_K.gguf) | Q6_K | 0.36GB |\n| [Qllama-.5B-RAG-1.Q8_0.gguf](https://huggingface.co/RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf/blob/main/Qllama-.5B-RAG-1.Q8_0.gguf) | Q8_0 | 0.47GB |\n\n\n\n\nOriginal model description:\n---\nlicense: mit\n---\nThis model needs further fine tuning.\n\nSee:\ntxtai-rag.py for rag implimentation with txt ai wikipedia. \n\nLlamafyd version of Qwen .5B further fine tuned 1 epoch on wiki, math, science, and chat datasets. Based on Cinder data. This model further fine tuned 1 epoch on rag data.\n\nRough list of final datasets:\nformatted_beaugogh-openorca-multiplechoice-10k.txt\nformatted_BYC-Sophie-samsum-chatgpt-summary.txt\nformatted_conversation_bio.txt\nformatted_conversation_create_cinder_1.txt\nformatted_conversation_Electrical-engineering.txt\nformatted_conversation_multiturn_stem.txt\nformatted_conversation_physics.txt\nformatted_conversation_qa_rag_chem_prog_dataset.txt\nformatted_conversation_qa_robot_ai_dataset.txt\nformatted_conversation_qa_shopify_dataset1_rag.txt\nformatted_conversation_qa_shopify_dataset_rag.txt\nformatted_dyumat-databricks-dolly-5k-rag-split.txt\nformatted_Hypoxiic-wikipedia-summary-subset1k-summary_token.txt\nformatted_neural-bridge-rag-dataset-12000.txt\nformatted_rachid16-rag_finetuning_data.txt\nformatted_tiny_stories_1_summary_token_tag_token-xaa.txt\nformatted_tiny_stories_2_summary_token_assistant-xah.txt\nmed_rag_small.txt\nz_formatted_cinder_test.txt\n\n",
"related_quantizations": []
},
"tags": [
"gguf",
"endpoints_compatible",
"region:us",
"conversational"
],
"likes": 0,
"downloads": 277,
"gated": false,
"private": false,
"last_modified": "2024-06-27T12:42:34.000Z",
"created_at": "2024-06-27T12:37:18.000Z",
"pipeline_tag": "",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "667d5cfea318b333a04e7f13",
"id": "RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf",
"modelId": "RichardErkhov/Josephgflowers_-_Qllama-.5B-RAG-1-gguf",
"sha": "67bcffa0f1f7eefb67833cdc3f9f93aa0f7132de",
"createdAt": "2024-06-27T12:37:18.000Z",
"lastModified": "2024-06-27T12:42:34.000Z",
"author": "RichardErkhov",
"downloads": 277,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "",
"library_name": "",
"siblings_count": 24
}