|
|
@@ -24,13 +24,28 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": null,
|
|
|
+ "execution_count": 1,
|
|
|
"id": "df27797f",
|
|
|
"metadata": {
|
|
|
+ "execution": {
|
|
|
+ "iopub.execute_input": "2023-11-27T22:21:40.880061Z",
|
|
|
+ "iopub.status.busy": "2023-11-27T22:21:40.879814Z",
|
|
|
+ "iopub.status.idle": "2023-11-27T22:21:41.598390Z",
|
|
|
+ "shell.execute_reply": "2023-11-27T22:21:41.598150Z",
|
|
|
+ "shell.execute_reply.started": "2023-11-27T22:21:40.880033Z"
|
|
|
+ },
|
|
|
"scrolled": true
|
|
|
},
|
|
|
"outputs": [],
|
|
|
- "source": []
|
|
|
+ "source": [
|
|
|
+ "from os import environ\n",
|
|
|
+ "from llama_index import SimpleDirectoryReader, ServiceContext, VectorStoreIndex\n",
|
|
|
+ "from llama_index.embeddings import HuggingFaceEmbedding\n",
|
|
|
+ "from llama_index.llms import LlamaCPP\n",
|
|
|
+ "from llama_index.llms.llama_utils import (messages_to_prompt, completion_to_prompt)\n",
|
|
|
+ "from llama_index.storage.storage_context import StorageContext\n",
|
|
|
+ "from llama_index.vector_stores import MilvusVectorStore"
|
|
|
+ ]
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "markdown",
|
|
|
@@ -42,9 +57,17 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": null,
|
|
|
+ "execution_count": 2,
|
|
|
"id": "08df0af5-5c2c-43f6-ae31-b5984cf55182",
|
|
|
- "metadata": {},
|
|
|
+ "metadata": {
|
|
|
+ "execution": {
|
|
|
+ "iopub.execute_input": "2023-11-27T22:21:41.599094Z",
|
|
|
+ "iopub.status.busy": "2023-11-27T22:21:41.598963Z",
|
|
|
+ "iopub.status.idle": "2023-11-27T22:21:41.601186Z",
|
|
|
+ "shell.execute_reply": "2023-11-27T22:21:41.601024Z",
|
|
|
+ "shell.execute_reply.started": "2023-11-27T22:21:41.599087Z"
|
|
|
+ }
|
|
|
+ },
|
|
|
"outputs": [],
|
|
|
"source": [
|
|
|
"environ[\"LLAMA_INDEX_CACHE_DIR\"] = \"dist\""
|
|
|
@@ -60,11 +83,410 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": null,
|
|
|
+ "execution_count": 3,
|
|
|
"id": "092108a6",
|
|
|
- "metadata": {},
|
|
|
- "outputs": [],
|
|
|
- "source": []
|
|
|
+ "metadata": {
|
|
|
+ "execution": {
|
|
|
+ "iopub.execute_input": "2023-11-27T22:21:41.601511Z",
|
|
|
+ "iopub.status.busy": "2023-11-27T22:21:41.601442Z",
|
|
|
+ "iopub.status.idle": "2023-11-27T22:21:43.104487Z",
|
|
|
+ "shell.execute_reply": "2023-11-27T22:21:43.104182Z",
|
|
|
+ "shell.execute_reply.started": "2023-11-27T22:21:41.601504Z"
|
|
|
+ }
|
|
|
+ },
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "name": "stderr",
|
|
|
+ "output_type": "stream",
|
|
|
+ "text": [
|
|
|
+ "ggml_init_cublas: GGML_CUDA_FORCE_MMQ: no\n",
|
|
|
+ "ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes\n",
|
|
|
+ "ggml_init_cublas: found 1 CUDA devices:\n",
|
|
|
+ " Device 0: NVIDIA GeForce RTX 4070 Ti, compute capability 8.9\n",
|
|
|
+ "llama_model_loader: loaded meta data with 20 key-value pairs and 291 tensors from dist/models/dolphin-2.2.1-mistral-7b.Q4_K_M.gguf?download=true (version GGUF V3 (latest))\n",
|
|
|
+ "llama_model_loader: - tensor 0: token_embd.weight q4_K [ 4096, 32002, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 1: blk.0.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 2: blk.0.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 3: blk.0.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 4: blk.0.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 5: blk.0.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 6: blk.0.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 7: blk.0.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 8: blk.0.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 9: blk.0.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 10: blk.1.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 11: blk.1.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 12: blk.1.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 13: blk.1.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 14: blk.1.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 15: blk.1.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 16: blk.1.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 17: blk.1.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 18: blk.1.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 19: blk.2.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 20: blk.2.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 21: blk.2.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 22: blk.2.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 23: blk.2.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 24: blk.2.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 25: blk.2.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 26: blk.2.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 27: blk.2.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 28: blk.3.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 29: blk.3.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 30: blk.3.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 31: blk.3.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 32: blk.3.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 33: blk.3.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 34: blk.3.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 35: blk.3.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 36: blk.3.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 37: blk.4.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 38: blk.4.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 39: blk.4.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 40: blk.4.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 41: blk.4.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 42: blk.4.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 43: blk.4.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 44: blk.4.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 45: blk.4.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 46: blk.5.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 47: blk.5.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 48: blk.5.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 49: blk.5.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 50: blk.5.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 51: blk.5.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 52: blk.5.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 53: blk.5.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 54: blk.5.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 55: blk.6.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 56: blk.6.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 57: blk.6.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 58: blk.6.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 59: blk.6.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 60: blk.6.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 61: blk.6.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 62: blk.6.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 63: blk.6.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 64: blk.7.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 65: blk.7.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 66: blk.7.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 67: blk.7.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 68: blk.7.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 69: blk.7.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 70: blk.7.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 71: blk.7.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 72: blk.7.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 73: blk.8.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 74: blk.8.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 75: blk.8.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 76: blk.8.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 77: blk.8.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 78: blk.8.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 79: blk.8.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 80: blk.8.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 81: blk.8.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 82: blk.9.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 83: blk.9.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 84: blk.9.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 85: blk.9.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 86: blk.9.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 87: blk.9.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 88: blk.9.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 89: blk.9.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 90: blk.9.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 91: blk.10.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 92: blk.10.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 93: blk.10.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 94: blk.10.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 95: blk.10.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 96: blk.10.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 97: blk.10.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 98: blk.10.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 99: blk.10.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 100: blk.11.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 101: blk.11.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 102: blk.11.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 103: blk.11.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 104: blk.11.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 105: blk.11.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 106: blk.11.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 107: blk.11.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 108: blk.11.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 109: blk.12.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 110: blk.12.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 111: blk.12.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 112: blk.12.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 113: blk.12.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 114: blk.12.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 115: blk.12.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 116: blk.12.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 117: blk.12.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 118: blk.13.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 119: blk.13.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 120: blk.13.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 121: blk.13.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 122: blk.13.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 123: blk.13.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 124: blk.13.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 125: blk.13.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 126: blk.13.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 127: blk.14.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 128: blk.14.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 129: blk.14.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 130: blk.14.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 131: blk.14.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 132: blk.14.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 133: blk.14.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 134: blk.14.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 135: blk.14.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 136: blk.15.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 137: blk.15.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 138: blk.15.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 139: blk.15.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 140: blk.15.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 141: blk.15.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 142: blk.15.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 143: blk.15.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 144: blk.15.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 145: blk.16.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 146: blk.16.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 147: blk.16.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 148: blk.16.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 149: blk.16.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 150: blk.16.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 151: blk.16.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 152: blk.16.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 153: blk.16.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 154: blk.17.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 155: blk.17.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 156: blk.17.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 157: blk.17.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 158: blk.17.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 159: blk.17.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 160: blk.17.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 161: blk.17.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 162: blk.17.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 163: blk.18.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 164: blk.18.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 165: blk.18.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 166: blk.18.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 167: blk.18.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 168: blk.18.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 169: blk.18.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 170: blk.18.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 171: blk.18.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 172: blk.19.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 173: blk.19.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 174: blk.19.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 175: blk.19.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 176: blk.19.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 177: blk.19.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 178: blk.19.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 179: blk.19.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 180: blk.19.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 181: blk.20.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 182: blk.20.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 183: blk.20.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 184: blk.20.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 185: blk.20.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 186: blk.20.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 187: blk.20.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 188: blk.20.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 189: blk.20.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 190: blk.21.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 191: blk.21.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 192: blk.21.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 193: blk.21.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 194: blk.21.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 195: blk.21.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 196: blk.21.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 197: blk.21.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 198: blk.21.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 199: blk.22.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 200: blk.22.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 201: blk.22.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 202: blk.22.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 203: blk.22.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 204: blk.22.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 205: blk.22.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 206: blk.22.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 207: blk.22.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 208: blk.23.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 209: blk.23.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 210: blk.23.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 211: blk.23.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 212: blk.23.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 213: blk.23.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 214: blk.23.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 215: blk.23.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 216: blk.23.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 217: blk.24.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 218: blk.24.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 219: blk.24.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 220: blk.24.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 221: blk.24.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 222: blk.24.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 223: blk.24.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 224: blk.24.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 225: blk.24.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 226: blk.25.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 227: blk.25.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 228: blk.25.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 229: blk.25.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 230: blk.25.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 231: blk.25.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 232: blk.25.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 233: blk.25.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 234: blk.25.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 235: blk.26.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 236: blk.26.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 237: blk.26.attn_v.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 238: blk.26.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 239: blk.26.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 240: blk.26.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 241: blk.26.ffn_down.weight q4_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 242: blk.26.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 243: blk.26.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 244: blk.27.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 245: blk.27.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 246: blk.27.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 247: blk.27.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 248: blk.27.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 249: blk.27.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 250: blk.27.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 251: blk.27.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 252: blk.27.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 253: blk.28.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 254: blk.28.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 255: blk.28.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 256: blk.28.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 257: blk.28.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 258: blk.28.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 259: blk.28.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 260: blk.28.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 261: blk.28.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 262: blk.29.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 263: blk.29.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 264: blk.29.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 265: blk.29.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 266: blk.29.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 267: blk.29.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 268: blk.29.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 269: blk.29.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 270: blk.29.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 271: blk.30.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 272: blk.30.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 273: blk.30.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 274: blk.30.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 275: blk.30.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 276: blk.30.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 277: blk.30.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 278: blk.30.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 279: blk.30.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 280: blk.31.attn_q.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 281: blk.31.attn_k.weight q4_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 282: blk.31.attn_v.weight q6_K [ 4096, 1024, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 283: blk.31.attn_output.weight q4_K [ 4096, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 284: blk.31.ffn_gate.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 285: blk.31.ffn_up.weight q4_K [ 4096, 14336, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 286: blk.31.ffn_down.weight q6_K [ 14336, 4096, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 287: blk.31.attn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 288: blk.31.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 289: output_norm.weight f32 [ 4096, 1, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - tensor 290: output.weight q6_K [ 4096, 32002, 1, 1 ]\n",
|
|
|
+ "llama_model_loader: - kv 0: general.architecture str = llama\n",
|
|
|
+ "llama_model_loader: - kv 1: general.name str = ehartford_dolphin-2.2.1-mistral-7b\n",
|
|
|
+ "llama_model_loader: - kv 2: llama.context_length u32 = 32768\n",
|
|
|
+ "llama_model_loader: - kv 3: llama.embedding_length u32 = 4096\n",
|
|
|
+ "llama_model_loader: - kv 4: llama.block_count u32 = 32\n",
|
|
|
+ "llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336\n",
|
|
|
+ "llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128\n",
|
|
|
+ "llama_model_loader: - kv 7: llama.attention.head_count u32 = 32\n",
|
|
|
+ "llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8\n",
|
|
|
+ "llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010\n",
|
|
|
+ "llama_model_loader: - kv 10: llama.rope.freq_base f32 = 10000.000000\n",
|
|
|
+ "llama_model_loader: - kv 11: general.file_type u32 = 15\n",
|
|
|
+ "llama_model_loader: - kv 12: tokenizer.ggml.model str = llama\n",
|
|
|
+ "llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,32002] = [\"<unk>\", \"<s>\", \"</s>\", \"<0x00>\", \"<...\n",
|
|
|
+ "llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,32002] = [0.000000, 0.000000, 0.000000, 0.0000...\n",
|
|
|
+ "llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,32002] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...\n",
|
|
|
+ "llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 1\n",
|
|
|
+ "llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 32000\n",
|
|
|
+ "llama_model_loader: - kv 18: tokenizer.ggml.padding_token_id u32 = 0\n",
|
|
|
+ "llama_model_loader: - kv 19: general.quantization_version u32 = 2\n",
|
|
|
+ "llama_model_loader: - type f32: 65 tensors\n",
|
|
|
+ "llama_model_loader: - type q4_K: 193 tensors\n",
|
|
|
+ "llama_model_loader: - type q6_K: 33 tensors\n",
|
|
|
+ "llm_load_vocab: special tokens definition check successful ( 261/32002 ).\n",
|
|
|
+ "llm_load_print_meta: format = GGUF V3 (latest)\n",
|
|
|
+ "llm_load_print_meta: arch = llama\n",
|
|
|
+ "llm_load_print_meta: vocab type = SPM\n",
|
|
|
+ "llm_load_print_meta: n_vocab = 32002\n",
|
|
|
+ "llm_load_print_meta: n_merges = 0\n",
|
|
|
+ "llm_load_print_meta: n_ctx_train = 32768\n",
|
|
|
+ "llm_load_print_meta: n_embd = 4096\n",
|
|
|
+ "llm_load_print_meta: n_head = 32\n",
|
|
|
+ "llm_load_print_meta: n_head_kv = 8\n",
|
|
|
+ "llm_load_print_meta: n_layer = 32\n",
|
|
|
+ "llm_load_print_meta: n_rot = 128\n",
|
|
|
+ "llm_load_print_meta: n_gqa = 4\n",
|
|
|
+ "llm_load_print_meta: f_norm_eps = 0.0e+00\n",
|
|
|
+ "llm_load_print_meta: f_norm_rms_eps = 1.0e-05\n",
|
|
|
+ "llm_load_print_meta: f_clamp_kqv = 0.0e+00\n",
|
|
|
+ "llm_load_print_meta: f_max_alibi_bias = 0.0e+00\n",
|
|
|
+ "llm_load_print_meta: n_ff = 14336\n",
|
|
|
+ "llm_load_print_meta: rope scaling = linear\n",
|
|
|
+ "llm_load_print_meta: freq_base_train = 10000.0\n",
|
|
|
+ "llm_load_print_meta: freq_scale_train = 1\n",
|
|
|
+ "llm_load_print_meta: n_yarn_orig_ctx = 32768\n",
|
|
|
+ "llm_load_print_meta: rope_finetuned = unknown\n",
|
|
|
+ "llm_load_print_meta: model type = 7B\n",
|
|
|
+ "llm_load_print_meta: model ftype = mostly Q4_K - Medium\n",
|
|
|
+ "llm_load_print_meta: model params = 7.24 B\n",
|
|
|
+ "llm_load_print_meta: model size = 4.07 GiB (4.83 BPW) \n",
|
|
|
+ "llm_load_print_meta: general.name = ehartford_dolphin-2.2.1-mistral-7b\n",
|
|
|
+ "llm_load_print_meta: BOS token = 1 '<s>'\n",
|
|
|
+ "llm_load_print_meta: EOS token = 32000 '<|im_end|>'\n",
|
|
|
+ "llm_load_print_meta: UNK token = 0 '<unk>'\n",
|
|
|
+ "llm_load_print_meta: PAD token = 0 '<unk>'\n",
|
|
|
+ "llm_load_print_meta: LF token = 13 '<0x0A>'\n",
|
|
|
+ "llm_load_tensors: ggml ctx size = 0.11 MiB\n",
|
|
|
+ "llm_load_tensors: using CUDA for GPU acceleration\n",
|
|
|
+ "llm_load_tensors: mem required = 70.42 MiB\n",
|
|
|
+ "llm_load_tensors: offloading 32 repeating layers to GPU\n",
|
|
|
+ "llm_load_tensors: offloading non-repeating layers to GPU\n",
|
|
|
+ "llm_load_tensors: offloaded 35/35 layers to GPU\n",
|
|
|
+ "llm_load_tensors: VRAM used: 4095.06 MiB\n",
|
|
|
+ "...............................................................................................\n",
|
|
|
+ "llama_new_context_with_model: n_ctx = 3900\n",
|
|
|
+ "llama_new_context_with_model: freq_base = 10000.0\n",
|
|
|
+ "llama_new_context_with_model: freq_scale = 1\n",
|
|
|
+ "llama_kv_cache_init: offloading v cache to GPU\n",
|
|
|
+ "llama_kv_cache_init: offloading k cache to GPU\n",
|
|
|
+ "llama_kv_cache_init: VRAM kv self = 487.50 MiB\n",
|
|
|
+ "llama_new_context_with_model: kv self size = 487.50 MiB\n",
|
|
|
+ "llama_build_graph: non-view tensors processed: 740/740\n",
|
|
|
+ "llama_new_context_with_model: compute buffer total size = 278.43 MiB\n",
|
|
|
+ "llama_new_context_with_model: VRAM scratch buffer: 275.37 MiB\n",
|
|
|
+ "llama_new_context_with_model: total VRAM used: 4857.93 MiB (model: 4095.06 MiB, context: 762.87 MiB)\n",
|
|
|
+ "AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | \n"
|
|
|
+ ]
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "llm = LlamaCPP(\n",
|
|
|
+ " completion_to_prompt=completion_to_prompt,\n",
|
|
|
+ " context_window=3900,\n",
|
|
|
+ " generate_kwargs={},\n",
|
|
|
+ " max_new_tokens=256,\n",
|
|
|
+ " messages_to_prompt=messages_to_prompt,\n",
|
|
|
+ " model_kwargs={\"n_gpu_layers\": -1},\n",
|
|
|
+ " model_url=\"https://huggingface.co/TheBloke/dolphin-2.2.1-mistral-7B-GGUF/resolve/main/dolphin-2.2.1-mistral-7b.Q4_K_M.gguf?download=true\",\n",
|
|
|
+ " temperature=0.1,\n",
|
|
|
+ " verbose=True\n",
|
|
|
+ ")"
|
|
|
+ ]
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "markdown",
|
|
|
@@ -76,11 +498,21 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": null,
|
|
|
+ "execution_count": 4,
|
|
|
"id": "baa95bb6",
|
|
|
- "metadata": {},
|
|
|
+ "metadata": {
|
|
|
+ "execution": {
|
|
|
+ "iopub.execute_input": "2023-11-27T22:21:43.104797Z",
|
|
|
+ "iopub.status.busy": "2023-11-27T22:21:43.104731Z",
|
|
|
+ "iopub.status.idle": "2023-11-27T22:21:46.190805Z",
|
|
|
+ "shell.execute_reply": "2023-11-27T22:21:46.190452Z",
|
|
|
+ "shell.execute_reply.started": "2023-11-27T22:21:43.104790Z"
|
|
|
+ }
|
|
|
+ },
|
|
|
"outputs": [],
|
|
|
- "source": []
|
|
|
+ "source": [
|
|
|
+ "embedding = HuggingFaceEmbedding(model_name=\"BAAI/bge-small-en-v1.5\")"
|
|
|
+ ]
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "markdown",
|
|
|
@@ -97,11 +529,22 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": null,
|
|
|
+ "execution_count": 5,
|
|
|
"id": "957c6f1c-31b7-40e8-ab18-02069802fe70",
|
|
|
- "metadata": {},
|
|
|
+ "metadata": {
|
|
|
+ "execution": {
|
|
|
+ "iopub.execute_input": "2023-11-27T22:21:46.191451Z",
|
|
|
+ "iopub.status.busy": "2023-11-27T22:21:46.191259Z",
|
|
|
+ "iopub.status.idle": "2023-11-27T22:21:49.803381Z",
|
|
|
+ "shell.execute_reply": "2023-11-27T22:21:49.801685Z",
|
|
|
+ "shell.execute_reply.started": "2023-11-27T22:21:46.191434Z"
|
|
|
+ }
|
|
|
+ },
|
|
|
"outputs": [],
|
|
|
- "source": []
|
|
|
+ "source": [
|
|
|
+ "vector_store = MilvusVectorStore(dim=384, overwrite=True)\n",
|
|
|
+ "storage_context = StorageContext.from_defaults(vector_store=vector_store)"
|
|
|
+ ]
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "markdown",
|
|
|
@@ -113,11 +556,21 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": null,
|
|
|
+ "execution_count": 6,
|
|
|
"id": "c59696a9-a8f7-41c3-86d5-af2a80ea7fea",
|
|
|
- "metadata": {},
|
|
|
+ "metadata": {
|
|
|
+ "execution": {
|
|
|
+ "iopub.execute_input": "2023-11-27T22:21:49.805297Z",
|
|
|
+ "iopub.status.busy": "2023-11-27T22:21:49.804935Z",
|
|
|
+ "iopub.status.idle": "2023-11-27T22:21:49.811369Z",
|
|
|
+ "shell.execute_reply": "2023-11-27T22:21:49.810479Z",
|
|
|
+ "shell.execute_reply.started": "2023-11-27T22:21:49.805263Z"
|
|
|
+ }
|
|
|
+ },
|
|
|
"outputs": [],
|
|
|
- "source": []
|
|
|
+ "source": [
|
|
|
+ "loader = SimpleDirectoryReader('./data', recursive=True, exclude_hidden=True)"
|
|
|
+ ]
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "markdown",
|
|
|
@@ -129,11 +582,23 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": null,
|
|
|
+ "execution_count": 7,
|
|
|
"id": "bca13d96",
|
|
|
- "metadata": {},
|
|
|
+ "metadata": {
|
|
|
+ "execution": {
|
|
|
+ "iopub.execute_input": "2023-11-27T22:21:49.815049Z",
|
|
|
+ "iopub.status.busy": "2023-11-27T22:21:49.814350Z",
|
|
|
+ "iopub.status.idle": "2023-11-27T22:21:50.704419Z",
|
|
|
+ "shell.execute_reply": "2023-11-27T22:21:50.704196Z",
|
|
|
+ "shell.execute_reply.started": "2023-11-27T22:21:49.815001Z"
|
|
|
+ }
|
|
|
+ },
|
|
|
"outputs": [],
|
|
|
- "source": []
|
|
|
+ "source": [
|
|
|
+ "service_context = ServiceContext.from_defaults(llm=llm, embed_model=embedding)\n",
|
|
|
+ "documents = loader.load_data()\n",
|
|
|
+ "index = VectorStoreIndex.from_documents(documents, service_context=service_context, storage_context=storage_context)"
|
|
|
+ ]
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "markdown",
|
|
|
@@ -145,11 +610,21 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": null,
|
|
|
+ "execution_count": 8,
|
|
|
"id": "097a8526",
|
|
|
- "metadata": {},
|
|
|
+ "metadata": {
|
|
|
+ "execution": {
|
|
|
+ "iopub.execute_input": "2023-11-27T22:21:50.704809Z",
|
|
|
+ "iopub.status.busy": "2023-11-27T22:21:50.704728Z",
|
|
|
+ "iopub.status.idle": "2023-11-27T22:21:50.870611Z",
|
|
|
+ "shell.execute_reply": "2023-11-27T22:21:50.870387Z",
|
|
|
+ "shell.execute_reply.started": "2023-11-27T22:21:50.704797Z"
|
|
|
+ }
|
|
|
+ },
|
|
|
"outputs": [],
|
|
|
- "source": []
|
|
|
+ "source": [
|
|
|
+ "query_engine = index.as_query_engine()"
|
|
|
+ ]
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "markdown",
|
|
|
@@ -161,11 +636,45 @@
|
|
|
},
|
|
|
{
|
|
|
"cell_type": "code",
|
|
|
- "execution_count": null,
|
|
|
+ "execution_count": 9,
|
|
|
"id": "7f4d8911",
|
|
|
- "metadata": {},
|
|
|
- "outputs": [],
|
|
|
- "source": []
|
|
|
+ "metadata": {
|
|
|
+ "execution": {
|
|
|
+ "iopub.execute_input": "2023-11-27T22:21:50.871034Z",
|
|
|
+ "iopub.status.busy": "2023-11-27T22:21:50.870903Z",
|
|
|
+ "iopub.status.idle": "2023-11-27T22:21:52.400251Z",
|
|
|
+ "shell.execute_reply": "2023-11-27T22:21:52.399855Z",
|
|
|
+ "shell.execute_reply.started": "2023-11-27T22:21:50.871027Z"
|
|
|
+ }
|
|
|
+ },
|
|
|
+ "outputs": [
|
|
|
+ {
|
|
|
+ "name": "stdout",
|
|
|
+ "output_type": "stream",
|
|
|
+ "text": [
|
|
|
+ " These files appear to be related to a real estate transaction involving multiple properties with different addresses in Cedar Park and San Antonio, Texas. The documents contain details such as property addresses, legal descriptions, purchase prices, loan amounts, and the names of involved parties like buyers, sellers, and settlement agencies.\n",
|
|
|
+ "{'596b3b27-9546-49b4-aae9-1987ce11e099': {'page_label': '2', 'file_name': 'Test.pdf', 'file_path': 'data/Test.pdf', 'file_type': 'application/pdf', 'file_size': 117715, 'creation_date': '2023-11-27', 'last_modified_date': '2023-11-10', 'last_accessed_date': '2023-11-27'}, '1f3342ca-d98d-4217-b7d1-d6dc83baa36b': {'page_label': '1', 'file_name': 'Test.pdf', 'file_path': 'data/Test.pdf', 'file_type': 'application/pdf', 'file_size': 117715, 'creation_date': '2023-11-27', 'last_modified_date': '2023-11-10', 'last_accessed_date': '2023-11-27'}}\n"
|
|
|
+ ]
|
|
|
+ },
|
|
|
+ {
|
|
|
+ "name": "stderr",
|
|
|
+ "output_type": "stream",
|
|
|
+ "text": [
|
|
|
+ "\n",
|
|
|
+ "llama_print_timings: load time = 155.73 ms\n",
|
|
|
+ "llama_print_timings: sample time = 8.36 ms / 63 runs ( 0.13 ms per token, 7534.08 tokens per second)\n",
|
|
|
+ "llama_print_timings: prompt eval time = 480.62 ms / 1289 tokens ( 0.37 ms per token, 2681.97 tokens per second)\n",
|
|
|
+ "llama_print_timings: eval time = 769.75 ms / 62 runs ( 12.42 ms per token, 80.55 tokens per second)\n",
|
|
|
+ "llama_print_timings: total time = 1315.94 ms\n"
|
|
|
+ ]
|
|
|
+ }
|
|
|
+ ],
|
|
|
+ "source": [
|
|
|
+ "response = query_engine.query(\"What are these files about?\")\n",
|
|
|
+ "\n",
|
|
|
+ "print(response)\n",
|
|
|
+ "print(response.metadata)"
|
|
|
+ ]
|
|
|
}
|
|
|
],
|
|
|
"metadata": {
|
