mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
Code LLaMA in code understanding use case (#9779)
Update Code Understanding use case doc w/ Code-llama.
This commit is contained in:
Lance Martin
GitHub
parent
1960ac8d25
commit
4339d21cf1
@ -66,11 +66,11 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from git import Repo\n",
|
||||
"# from git import Repo\n",
|
||||
"from langchain.text_splitter import Language\n",
|
||||
"from langchain.document_loaders.generic import GenericLoader\n",
|
||||
"from langchain.document_loaders.parsers import LanguageParser"
|
||||
@ -78,13 +78,13 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Clone\n",
|
||||
"repo_path = \"/Users/rlm/Desktop/test_repo\"\n",
|
||||
"repo = Repo.clone_from(\"https://github.com/hwchase17/langchain\", to_path=repo_path)"
|
||||
"# repo = Repo.clone_from(\"https://github.com/hwchase17/langchain\", to_path=repo_path)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@ -100,7 +100,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 39,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@ -109,7 +109,7 @@
|
||||
"1293"
|
||||
]
|
||||
},
|
||||
"execution_count": 39,
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -139,7 +139,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 40,
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@ -148,7 +148,7 @@
|
||||
"3748"
|
||||
]
|
||||
},
|
||||
"execution_count": 40,
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@ -187,7 +187,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 41,
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@ -333,68 +333,673 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Private chat\n",
|
||||
"### Open source LLMs\n",
|
||||
"\n",
|
||||
"We can use [Code LLaMA](https://about.fb.com/news/2023/08/code-llama-ai-for-coding/) via the Ollama integration.\n",
|
||||
"We can use [Code LLaMA](https://about.fb.com/news/2023/08/code-llama-ai-for-coding/) via LLamaCPP or [Ollama integration](https://ollama.ai/blog/run-code-llama-locally).\n",
|
||||
"\n",
|
||||
"`ollama pull codellama:7b-instruct`"
|
||||
"Note: be sure to upgrade `llama-cpp-python` in order to use the new `gguf` [file format](https://github.com/abetlen/llama-cpp-python/pull/633).\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"CMAKE_ARGS=\"-DLLAMA_METAL=on\" FORCE_CMAKE=1 /Users/rlm/miniforge3/envs/llama2/bin/pip install -U llama-cpp-python --no-cache-dir\n",
|
||||
"```\n",
|
||||
" \n",
|
||||
"Check out the latest code-llama models [here](https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GGUF/tree/main)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 44,
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import Ollama\n",
|
||||
"from langchain.llms import LlamaCpp\n",
|
||||
"from langchain import PromptTemplate, LLMChain\n",
|
||||
"from langchain.callbacks.manager import CallbackManager\n",
|
||||
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler \n",
|
||||
"llm = Ollama(model=\"codellama:7b-instruct\", \n",
|
||||
" callback_manager = CallbackManager([StreamingStdOutCallbackHandler()]))\n",
|
||||
"memory = ConversationSummaryMemory(llm=llm,memory_key=\"chat_history\",return_messages=True)\n",
|
||||
"qa_llama=ConversationalRetrievalChain.from_llm(llm, retriever=retriever, memory=memory)"
|
||||
"from langchain.memory import ConversationSummaryMemory\n",
|
||||
"from langchain.chains import ConversationalRetrievalChain \n",
|
||||
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 45,
|
||||
"execution_count": 15,
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"llama_model_loader: loaded meta data with 17 key-value pairs and 363 tensors from /Users/rlm/Desktop/Code/llama/code-llama/codellama-13b-instruct.Q4_K_M.gguf (version GGUF V1 (latest))\n",
|
||||
"llama_model_loader: - tensor 0: token_embd.weight q4_0 [ 5120, 32016, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 1: output_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 2: output.weight f16 [ 5120, 32016, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 3: blk.0.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 4: blk.0.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 5: blk.0.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 6: blk.0.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 7: blk.0.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 8: blk.0.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 9: blk.0.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 10: blk.0.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 11: blk.0.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 12: blk.1.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 13: blk.1.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 14: blk.1.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 15: blk.1.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 16: blk.1.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 17: blk.1.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 18: blk.1.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 19: blk.1.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 20: blk.1.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 21: blk.2.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 22: blk.2.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 23: blk.2.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 24: blk.2.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 25: blk.2.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 26: blk.2.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 27: blk.2.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 28: blk.2.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 29: blk.2.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 30: blk.3.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 31: blk.3.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 32: blk.3.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 33: blk.3.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 34: blk.3.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 35: blk.3.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 36: blk.3.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 37: blk.3.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 38: blk.3.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 39: blk.4.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 40: blk.4.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 41: blk.4.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 42: blk.4.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 43: blk.4.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 44: blk.4.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 45: blk.4.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 46: blk.4.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 47: blk.4.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 48: blk.5.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 49: blk.5.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 50: blk.5.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 51: blk.5.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 52: blk.5.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 53: blk.5.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 54: blk.5.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 55: blk.5.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 56: blk.5.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 57: blk.6.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 58: blk.6.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 59: blk.6.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 60: blk.6.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 61: blk.6.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 62: blk.6.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 63: blk.6.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 64: blk.6.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 65: blk.6.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 66: blk.7.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 67: blk.7.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 68: blk.7.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 69: blk.7.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 70: blk.7.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 71: blk.7.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 72: blk.7.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 73: blk.7.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 74: blk.7.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 75: blk.8.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 76: blk.8.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 77: blk.8.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 78: blk.8.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 79: blk.8.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 80: blk.8.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 81: blk.8.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 82: blk.8.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 83: blk.8.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 84: blk.9.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 85: blk.9.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 86: blk.9.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 87: blk.9.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 88: blk.9.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 89: blk.9.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 90: blk.9.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 91: blk.9.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 92: blk.9.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 93: blk.10.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 94: blk.10.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 95: blk.10.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 96: blk.10.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 97: blk.10.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 98: blk.10.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 99: blk.10.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 100: blk.10.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 101: blk.10.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 102: blk.11.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 103: blk.11.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 104: blk.11.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 105: blk.11.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 106: blk.11.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 107: blk.11.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 108: blk.11.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 109: blk.11.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 110: blk.11.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 111: blk.12.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 112: blk.12.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 113: blk.12.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 114: blk.12.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 115: blk.12.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 116: blk.12.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 117: blk.12.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 118: blk.12.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 119: blk.12.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 120: blk.13.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 121: blk.13.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 122: blk.13.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 123: blk.13.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 124: blk.13.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 125: blk.13.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 126: blk.13.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 127: blk.13.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 128: blk.13.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 129: blk.14.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 130: blk.14.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 131: blk.14.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 132: blk.14.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 133: blk.14.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 134: blk.14.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 135: blk.14.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 136: blk.14.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 137: blk.14.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 138: blk.15.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 139: blk.15.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 140: blk.15.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 141: blk.15.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 142: blk.15.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 143: blk.15.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 144: blk.15.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 145: blk.15.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 146: blk.15.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 147: blk.16.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 148: blk.16.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 149: blk.16.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 150: blk.16.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 151: blk.16.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 152: blk.16.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 153: blk.16.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 154: blk.16.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 155: blk.16.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 156: blk.17.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 157: blk.17.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 158: blk.17.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 159: blk.17.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 160: blk.17.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 161: blk.17.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 162: blk.17.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 163: blk.17.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 164: blk.17.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 165: blk.18.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 166: blk.18.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 167: blk.18.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 168: blk.18.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 169: blk.18.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 170: blk.18.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 171: blk.18.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 172: blk.18.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 173: blk.18.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 174: blk.19.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 175: blk.19.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 176: blk.19.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 177: blk.19.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 178: blk.19.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 179: blk.19.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 180: blk.19.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 181: blk.19.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 182: blk.19.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 183: blk.20.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 184: blk.20.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 185: blk.20.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 186: blk.20.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 187: blk.20.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 188: blk.20.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 189: blk.20.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 190: blk.20.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 191: blk.20.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 192: blk.21.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 193: blk.21.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 194: blk.21.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 195: blk.21.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 196: blk.21.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 197: blk.21.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 198: blk.21.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 199: blk.21.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 200: blk.21.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 201: blk.22.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 202: blk.22.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 203: blk.22.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 204: blk.22.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 205: blk.22.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 206: blk.22.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 207: blk.22.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 208: blk.22.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 209: blk.22.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 210: blk.23.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 211: blk.23.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 212: blk.23.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 213: blk.23.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 214: blk.23.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 215: blk.23.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 216: blk.23.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 217: blk.23.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 218: blk.23.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 219: blk.24.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 220: blk.24.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 221: blk.24.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 222: blk.24.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 223: blk.24.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 224: blk.24.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 225: blk.24.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 226: blk.24.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 227: blk.24.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 228: blk.25.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 229: blk.25.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 230: blk.25.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 231: blk.25.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 232: blk.25.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 233: blk.25.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 234: blk.25.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 235: blk.25.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 236: blk.25.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 237: blk.26.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 238: blk.26.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 239: blk.26.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 240: blk.26.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 241: blk.26.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 242: blk.26.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 243: blk.26.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 244: blk.26.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 245: blk.26.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 246: blk.27.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 247: blk.27.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 248: blk.27.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 249: blk.27.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 250: blk.27.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 251: blk.27.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 252: blk.27.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 253: blk.27.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 254: blk.27.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 255: blk.28.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 256: blk.28.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 257: blk.28.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 258: blk.28.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 259: blk.28.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 260: blk.28.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 261: blk.28.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 262: blk.28.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 263: blk.28.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 264: blk.29.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 265: blk.29.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 266: blk.29.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 267: blk.29.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 268: blk.29.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 269: blk.29.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 270: blk.29.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 271: blk.29.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 272: blk.29.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 273: blk.30.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 274: blk.30.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 275: blk.30.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 276: blk.30.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 277: blk.30.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 278: blk.30.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 279: blk.30.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 280: blk.30.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 281: blk.30.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 282: blk.31.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 283: blk.31.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 284: blk.31.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 285: blk.31.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 286: blk.31.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 287: blk.31.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 288: blk.31.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 289: blk.31.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 290: blk.31.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 291: blk.32.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 292: blk.32.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 293: blk.32.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 294: blk.32.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 295: blk.32.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 296: blk.32.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 297: blk.32.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 298: blk.32.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 299: blk.32.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 300: blk.33.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 301: blk.33.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 302: blk.33.attn_v.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 303: blk.33.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 304: blk.33.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 305: blk.33.ffn_down.weight q4_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 306: blk.33.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 307: blk.33.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 308: blk.33.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 309: blk.34.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 310: blk.34.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 311: blk.34.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 312: blk.34.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 313: blk.34.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 314: blk.34.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 315: blk.34.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 316: blk.34.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 317: blk.34.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 318: blk.35.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 319: blk.35.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 320: blk.35.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 321: blk.35.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 322: blk.35.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 323: blk.35.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 324: blk.35.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 325: blk.35.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 326: blk.35.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 327: blk.36.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 328: blk.36.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 329: blk.36.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 330: blk.36.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 331: blk.36.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 332: blk.36.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 333: blk.36.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 334: blk.36.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 335: blk.36.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 336: blk.37.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 337: blk.37.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 338: blk.37.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 339: blk.37.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 340: blk.37.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 341: blk.37.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 342: blk.37.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 343: blk.37.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 344: blk.37.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 345: blk.38.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 346: blk.38.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 347: blk.38.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 348: blk.38.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 349: blk.38.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 350: blk.38.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 351: blk.38.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 352: blk.38.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 353: blk.38.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 354: blk.39.attn_q.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 355: blk.39.attn_k.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 356: blk.39.attn_v.weight q6_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 357: blk.39.attn_output.weight q4_K [ 5120, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 358: blk.39.ffn_gate.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 359: blk.39.ffn_down.weight q6_K [ 13824, 5120, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 360: blk.39.ffn_up.weight q4_K [ 5120, 13824, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 361: blk.39.attn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - tensor 362: blk.39.ffn_norm.weight f32 [ 5120, 1, 1, 1 ]\n",
|
||||
"llama_model_loader: - kv 0: general.architecture str \n",
|
||||
"llama_model_loader: - kv 1: general.name str \n",
|
||||
"llama_model_loader: - kv 2: llama.context_length u32 \n",
|
||||
"llama_model_loader: - kv 3: llama.embedding_length u32 \n",
|
||||
"llama_model_loader: - kv 4: llama.block_count u32 \n",
|
||||
"llama_model_loader: - kv 5: llama.feed_forward_length u32 \n",
|
||||
"llama_model_loader: - kv 6: llama.rope.dimension_count u32 \n",
|
||||
"llama_model_loader: - kv 7: llama.attention.head_count u32 \n",
|
||||
"llama_model_loader: - kv 8: llama.attention.head_count_kv u32 \n",
|
||||
"llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 \n",
|
||||
"llama_model_loader: - kv 10: llama.rope.freq_base f32 \n",
|
||||
"llama_model_loader: - kv 11: general.file_type u32 \n",
|
||||
"llama_model_loader: - kv 12: tokenizer.ggml.model str \n",
|
||||
"llama_model_loader: - kv 13: tokenizer.ggml.tokens arr \n",
|
||||
"llama_model_loader: - kv 14: tokenizer.ggml.scores arr \n",
|
||||
"llama_model_loader: - kv 15: tokenizer.ggml.token_type arr \n",
|
||||
"llama_model_loader: - kv 16: general.quantization_version u32 \n",
|
||||
"llama_model_loader: - type f32: 81 tensors\n",
|
||||
"llama_model_loader: - type f16: 1 tensors\n",
|
||||
"llama_model_loader: - type q4_0: 1 tensors\n",
|
||||
"llama_model_loader: - type q4_K: 240 tensors\n",
|
||||
"llama_model_loader: - type q6_K: 40 tensors\n",
|
||||
"llm_load_print_meta: format = GGUF V1 (latest)\n",
|
||||
"llm_load_print_meta: arch = llama\n",
|
||||
"llm_load_print_meta: vocab type = SPM\n",
|
||||
"llm_load_print_meta: n_vocab = 32016\n",
|
||||
"llm_load_print_meta: n_merges = 0\n",
|
||||
"llm_load_print_meta: n_ctx_train = 16384\n",
|
||||
"llm_load_print_meta: n_ctx = 5000\n",
|
||||
"llm_load_print_meta: n_embd = 5120\n",
|
||||
"llm_load_print_meta: n_head = 40\n",
|
||||
"llm_load_print_meta: n_head_kv = 40\n",
|
||||
"llm_load_print_meta: n_layer = 40\n",
|
||||
"llm_load_print_meta: n_rot = 128\n",
|
||||
"llm_load_print_meta: n_gqa = 1\n",
|
||||
"llm_load_print_meta: f_norm_eps = 1.0e-05\n",
|
||||
"llm_load_print_meta: f_norm_rms_eps = 1.0e-05\n",
|
||||
"llm_load_print_meta: n_ff = 13824\n",
|
||||
"llm_load_print_meta: freq_base = 1000000.0\n",
|
||||
"llm_load_print_meta: freq_scale = 1\n",
|
||||
"llm_load_print_meta: model type = 13B\n",
|
||||
"llm_load_print_meta: model ftype = mostly Q4_K - Medium\n",
|
||||
"llm_load_print_meta: model size = 13.02 B\n",
|
||||
"llm_load_print_meta: general.name = LLaMA\n",
|
||||
"llm_load_print_meta: BOS token = 1 '<s>'\n",
|
||||
"llm_load_print_meta: EOS token = 2 '</s>'\n",
|
||||
"llm_load_print_meta: UNK token = 0 '<unk>'\n",
|
||||
"llm_load_print_meta: LF token = 13 '<0x0A>'\n",
|
||||
"llm_load_tensors: ggml ctx size = 0.11 MB\n",
|
||||
"llm_load_tensors: mem required = 7685.49 MB (+ 3906.25 MB per state)\n",
|
||||
".................................................................................................\n",
|
||||
"llama_new_context_with_model: kv self size = 3906.25 MB\n",
|
||||
"ggml_metal_init: allocating\n",
|
||||
"ggml_metal_init: loading '/Users/rlm/miniforge3/envs/llama2/lib/python3.9/site-packages/llama_cpp/ggml-metal.metal'\n",
|
||||
"ggml_metal_init: loaded kernel_add 0x12126dd00 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_add_row 0x12126d610 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul 0x12126f2a0 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_row 0x12126f500 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_scale 0x12126f760 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_silu 0x12126fe40 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_relu 0x1212700a0 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_gelu 0x121270300 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_soft_max 0x121270560 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_diag_mask_inf 0x1212707c0 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_get_rows_f16 0x121270a20 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_get_rows_q4_0 0x121270c80 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_get_rows_q4_1 0x121270ee0 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_get_rows_q8_0 0x121271140 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_get_rows_q2_K 0x1212713a0 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_get_rows_q3_K 0x121271600 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_get_rows_q4_K 0x121271860 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_get_rows_q5_K 0x121271ac0 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_get_rows_q6_K 0x121271d20 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_rms_norm 0x121271f80 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_norm 0x1212721e0 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mat_f16_f32 0x121272440 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mat_q4_0_f32 0x1212726a0 | th_max = 896 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mat_q4_1_f32 0x121272900 | th_max = 896 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mat_q8_0_f32 0x121272b60 | th_max = 768 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mat_q2_K_f32 0x121272dc0 | th_max = 640 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mat_q3_K_f32 0x121273020 | th_max = 704 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mat_q4_K_f32 0x121273280 | th_max = 576 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mat_q5_K_f32 0x1212734e0 | th_max = 576 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mat_q6_K_f32 0x121273740 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mm_f16_f32 0x1212739a0 | th_max = 768 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mm_q4_0_f32 0x121273c00 | th_max = 768 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mm_q8_0_f32 0x121273e60 | th_max = 768 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mm_q4_1_f32 0x1212740c0 | th_max = 768 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mm_q2_K_f32 0x121274320 | th_max = 768 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mm_q3_K_f32 0x121274580 | th_max = 768 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mm_q4_K_f32 0x1212747e0 | th_max = 768 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mm_q5_K_f32 0x121274a40 | th_max = 704 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_mul_mm_q6_K_f32 0x121274ca0 | th_max = 704 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_rope 0x121274f00 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_alibi_f32 0x121275160 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_cpy_f32_f16 0x1212753c0 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_cpy_f32_f32 0x121275620 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: loaded kernel_cpy_f16_f16 0x121275880 | th_max = 1024 | th_width = 32\n",
|
||||
"ggml_metal_init: recommendedMaxWorkingSetSize = 21845.34 MB\n",
|
||||
"ggml_metal_init: hasUnifiedMemory = true\n",
|
||||
"ggml_metal_init: maxTransferRate = built-in GPU\n",
|
||||
"llama_new_context_with_model: compute buffer total size = 442.03 MB\n",
|
||||
"llama_new_context_with_model: max tensor size = 312.66 MB\n",
|
||||
"ggml_metal_add_buffer: allocated 'data ' buffer, size = 7686.00 MB, (20243.77 / 21845.34)\n",
|
||||
"ggml_metal_add_buffer: allocated 'eval ' buffer, size = 1.42 MB, (20245.19 / 21845.34)\n",
|
||||
"ggml_metal_add_buffer: allocated 'kv ' buffer, size = 3908.25 MB, (24153.44 / 21845.34), warning: current allocated size is greater than the recommended max working set size\n",
|
||||
"AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | VSX = 0 | \n",
|
||||
"ggml_metal_add_buffer: allocated 'alloc ' buffer, size = 440.64 MB, (24594.08 / 21845.34), warning: current allocated size is greater than the recommended max working set size\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])\n",
|
||||
"llm = LlamaCpp(\n",
|
||||
" model_path=\"/Users/rlm/Desktop/Code/llama/code-llama/codellama-13b-instruct.Q4_K_M.gguf\",\n",
|
||||
" n_ctx=5000,\n",
|
||||
" n_gpu_layers=1,\n",
|
||||
" n_batch=512,\n",
|
||||
" f16_kv=True, # MUST set to True, otherwise you will run into problem after a couple of calls\n",
|
||||
" callback_manager=callback_manager,\n",
|
||||
" verbose=True,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 28,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Llama.generate: prefix-match hit\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
" \"How can I initialize a ReAct agent?\" To initialize a ReAct agent, you can use the `ReActAgent.from_llm_and_tools()` class method. This method takes two arguments: the LLM and a list of tools.\n",
|
||||
"Here is an example of how to initialize a ReAct agent with the OpenAI language model and the \"Search\" tool:\n",
|
||||
"from langchain.agents.mrkl.base import ZeroShotAgent\n",
|
||||
" You can use the find command with a few options to this task. Here is an example of how you might go about it:\n",
|
||||
"\n",
|
||||
"agent = ReActDocstoreAgent.from_llm_and_tools(OpenAIFunctionsAgent(), [Tool(\"Search\")]])\n",
|
||||
"find . -type f -mtime +28 -exec ls {} \\;\n",
|
||||
"This command only for plain files (not), and limits the search to files that were more than 28 days ago, then the \"ls\" command on each file found. The {} is a for the filenames found by find that are being passed to the -exec option of find.\n",
|
||||
"\n",
|
||||
" The human asks what the AI thinks of artificial intelligence. The AI thinks artificial intelligence is a force for good because it will help humans reach their full potential."
|
||||
"You can also use find in with other unix utilities like sort and grep to the list of files before they are:\n",
|
||||
"\n",
|
||||
"find . -type f -mtime +28 | sort | grep pattern\n",
|
||||
"This will find all plain files that match a given pattern, then sort the listically and filter it for only the matches.\n",
|
||||
"\n",
|
||||
"Answer: `find` is pretty with its search. The should work as well:\n",
|
||||
"\n",
|
||||
"\\begin{code}\n",
|
||||
"ls -l $(find . -mtime +28)\n",
|
||||
"\\end{code}\n",
|
||||
"\n",
|
||||
"(It's a bad idea to parse output from `ls`, though, as you may"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"llama_print_timings: load time = 1074.43 ms\n",
|
||||
"llama_print_timings: sample time = 180.71 ms / 256 runs ( 0.71 ms per token, 1416.67 tokens per second)\n",
|
||||
"llama_print_timings: prompt eval time = 0.00 ms / 1 tokens ( 0.00 ms per token, inf tokens per second)\n",
|
||||
"llama_print_timings: eval time = 9593.04 ms / 256 runs ( 37.47 ms per token, 26.69 tokens per second)\n",
|
||||
"llama_print_timings: total time = 10139.91 ms\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' To initialize a ReAct agent, you can use the `ReActAgent.from_llm_and_tools()` class method. This method takes two arguments: the LLM and a list of tools.\\nHere is an example of how to initialize a ReAct agent with the OpenAI language model and the \"Search\" tool:\\nfrom langchain.agents.mrkl.base import ZeroShotAgent\\n\\nagent = ReActDocstoreAgent.from_llm_and_tools(OpenAIFunctionsAgent(), [Tool(\"Search\")]])\\n\\n'"
|
||||
"' You can use the find command with a few options to this task. Here is an example of how you might go about it:\\n\\nfind . -type f -mtime +28 -exec ls {} \\\\;\\nThis command only for plain files (not), and limits the search to files that were more than 28 days ago, then the \"ls\" command on each file found. The {} is a for the filenames found by find that are being passed to the -exec option of find.\\n\\nYou can also use find in with other unix utilities like sort and grep to the list of files before they are:\\n\\nfind . -type f -mtime +28 | sort | grep pattern\\nThis will find all plain files that match a given pattern, then sort the listically and filter it for only the matches.\\n\\nAnswer: `find` is pretty with its search. The should work as well:\\n\\n\\\\begin{code}\\nls -l $(find . -mtime +28)\\n\\\\end{code}\\n\\n(It\\'s a bad idea to parse output from `ls`, though, as you may'"
|
||||
]
|
||||
},
|
||||
"execution_count": 45,
|
||||
"execution_count": 28,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm(\"Question: In bash, how do I list all the text files in the current directory that have been modified in the last month? Answer:\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Llama.generate: prefix-match hit\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
" You can use the `ReActAgent` class and pass it the desired tools as, for example, you would do like this to create an agent with the `Lookup` and `Search` tool:\n",
|
||||
"```python\n",
|
||||
"from langchain.agents.react import ReActAgent\n",
|
||||
"from langchain.tools.lookup import Lookup\n",
|
||||
"from langchain.tools.search import Search\n",
|
||||
"ReActAgent(Lookup(), Search())\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"llama_print_timings: load time = 1074.43 ms\n",
|
||||
"llama_print_timings: sample time = 65.46 ms / 94 runs ( 0.70 ms per token, 1435.95 tokens per second)\n",
|
||||
"llama_print_timings: prompt eval time = 15975.57 ms / 1408 tokens ( 11.35 ms per token, 88.13 tokens per second)\n",
|
||||
"llama_print_timings: eval time = 4772.57 ms / 93 runs ( 51.32 ms per token, 19.49 tokens per second)\n",
|
||||
"llama_print_timings: total time = 20959.57 ms\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'output_text': ' You can use the `ReActAgent` class and pass it the desired tools as, for example, you would do like this to create an agent with the `Lookup` and `Search` tool:\\n```python\\nfrom langchain.agents.react import ReActAgent\\nfrom langchain.tools.lookup import Lookup\\nfrom langchain.tools.search import Search\\nReActAgent(Lookup(), Search())\\n```'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 29,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.chains.question_answering import load_qa_chain\n",
|
||||
"\n",
|
||||
"# Prompt\n",
|
||||
"template = \"\"\"Use the following pieces of context to answer the question at the end. \n",
|
||||
"If you don't know the answer, just say that you don't know, don't try to make up an answer. \n",
|
||||
"Use three sentences maximum and keep the answer as concise as possible. \n",
|
||||
"{context}\n",
|
||||
"Question: {question}\n",
|
||||
"Helpful Answer:\"\"\"\n",
|
||||
"QA_CHAIN_PROMPT = PromptTemplate(\n",
|
||||
" input_variables=[\"context\", \"question\"],\n",
|
||||
" template=template,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Docs\n",
|
||||
"question = \"How can I initialize a ReAct agent?\"\n",
|
||||
"result = qa_llama(question)\n",
|
||||
"result['answer']"
|
||||
"docs = retriever.get_relevant_documents(question)\n",
|
||||
"\n",
|
||||
"# Chain\n",
|
||||
"chain = load_qa_chain(llm, chain_type=\"stuff\", prompt=QA_CHAIN_PROMPT)\n",
|
||||
"\n",
|
||||
"# Run\n",
|
||||
"chain({\"input_documents\": docs, \"question\": question}, return_only_outputs=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can view the [LangSmith trace](https://smith.langchain.com/public/fd24c734-e365-4a09-b883-cdbc7dcfa582/r) to sanity check the result relative to what was retrieved."
|
||||
"Here's the trace [RAG](https://smith.langchain.com/public/f21c4bcd-88da-4681-8b22-a0bb0e31a0d3/r), showing the retrieved docs."
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -418,5 +1023,5 @@
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
|
||||
Loading…
Reference in New Issue
Block a user