books/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-10 12:33:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Uv workflow improvements (#531)

Browse Source 
* Uv workflow improvements

* Uv workflow improvements

* linter improvements

* pytproject.toml fixes

* pytproject.toml fixes

* pytproject.toml fixes

* pytproject.toml fixes

* pytproject.toml fixes

* pytproject.toml fixes

* windows fixes

* windows fixes

* windows fixes

* windows fixes

* windows fixes

* windows fixes

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix

* win32 fix
This commit is contained in:
Sebastian Raschka
2025-02-16 13:16:51 -06:00
committed by GitHub
parent 2f0afedaa7
commit 5016499d1d
29 changed files with 382 additions and 321 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
ch05/02_alternative_weight_loading/weight-loading-hf-safetensors.ipynb
View File

@@ -95,7 +95,7 @@
"metadata": {},
"outputs": [],
"source": [
"from previous_chapters import GPTModel, generate_text_simple"
"from previous_chapters import GPTModel"
]
},
{
@@ -242,7 +242,6 @@
"outputs": [],
"source": [
"import torch\n",
"from previous_chapters import GPTModel\n",
"\n",
"\n",
"gpt = GPTModel(BASE_CONFIG)\n",
@@ -306,7 +305,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.10.16"
}
},
"nbformat": 4,

6
ch05/02_alternative_weight_loading/weight-loading-hf-transformers.ipynb
View File

@@ -217,8 +217,8 @@
" gpt.trf_blocks[b].norm2.scale = assign_check(gpt.trf_blocks[b].norm2.scale, d[f\"h.{b}.ln_2.weight\"])\n",
" gpt.trf_blocks[b].norm2.shift = assign_check(gpt.trf_blocks[b].norm2.shift, d[f\"h.{b}.ln_2.bias\"])\n",
" \n",
" gpt.final_norm.scale = assign_check(gpt.final_norm.scale, d[f\"ln_f.weight\"])\n",
" gpt.final_norm.shift = assign_check(gpt.final_norm.shift, d[f\"ln_f.bias\"])\n",
" gpt.final_norm.scale = assign_check(gpt.final_norm.scale, d[\"ln_f.weight\"])\n",
" gpt.final_norm.shift = assign_check(gpt.final_norm.shift, d[\"ln_f.bias\"])\n",
" gpt.out_head.weight = assign_check(gpt.out_head.weight, d[\"wte.weight\"])"
]
},
@@ -293,7 +293,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.10.16"
}
},
"nbformat": 4,

5
ch05/07_gpt_to_llama/converting-llama2-to-llama3.ipynb
View File

@@ -1114,7 +1114,6 @@
},
"outputs": [],
"source": [
"import os\n",
"from pathlib import Path\n",
"\n",
"import tiktoken\n",
@@ -2633,7 +2632,7 @@
"source": [
"weights_file = hf_hub_download(\n",
" repo_id=\"meta-llama/Llama-3.2-1B\",\n",
" filename=f\"model.safetensors\",\n",
" filename=\"model.safetensors\",\n",
" local_dir=\"Llama-3.2-1B\"\n",
")\n",
"current_weights = load_file(weights_file)\n",
@@ -2747,7 +2746,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.10.16"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {

4
ch05/07_gpt_to_llama/standalone-llama32.ipynb
View File

@@ -993,7 +993,7 @@
"if LLAMA_SIZE_STR == \"1B\":\n",
" weights_file = hf_hub_download(\n",
" repo_id=f\"meta-llama/Llama-3.2-{LLAMA_SIZE_STR}-Instruct\",\n",
" filename=f\"model.safetensors\",\n",
" filename=\"model.safetensors\",\n",
" local_dir=f\"Llama-3.2-{LLAMA_SIZE_STR}-Instruct\"\n",
" )\n",
" combined_weights = load_file(weights_file)\n",
@@ -1213,7 +1213,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.10.16"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {