Instructions to use Karajan42/open_llama_dolly with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Karajan42/open_llama_dolly with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Karajan42/open_llama_dolly")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Karajan42/open_llama_dolly") model = AutoModelForMultimodalLM.from_pretrained("Karajan42/open_llama_dolly") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Karajan42/open_llama_dolly with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Karajan42/open_llama_dolly" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Karajan42/open_llama_dolly", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Karajan42/open_llama_dolly
- SGLang
How to use Karajan42/open_llama_dolly with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Karajan42/open_llama_dolly" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Karajan42/open_llama_dolly", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Karajan42/open_llama_dolly" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Karajan42/open_llama_dolly", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Karajan42/open_llama_dolly with Docker Model Runner:
docker model run hf.co/Karajan42/open_llama_dolly
Upload 45 files
Browse files- config.json +23 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00039.bin +3 -0
- pytorch_model-00002-of-00039.bin +3 -0
- pytorch_model-00003-of-00039.bin +3 -0
- pytorch_model-00004-of-00039.bin +3 -0
- pytorch_model-00005-of-00039.bin +3 -0
- pytorch_model-00006-of-00039.bin +3 -0
- pytorch_model-00007-of-00039.bin +3 -0
- pytorch_model-00008-of-00039.bin +3 -0
- pytorch_model-00009-of-00039.bin +3 -0
- pytorch_model-00010-of-00039.bin +3 -0
- pytorch_model-00011-of-00039.bin +3 -0
- pytorch_model-00012-of-00039.bin +3 -0
- pytorch_model-00013-of-00039.bin +3 -0
- pytorch_model-00014-of-00039.bin +3 -0
- pytorch_model-00015-of-00039.bin +3 -0
- pytorch_model-00016-of-00039.bin +3 -0
- pytorch_model-00017-of-00039.bin +3 -0
- pytorch_model-00018-of-00039.bin +3 -0
- pytorch_model-00019-of-00039.bin +3 -0
- pytorch_model-00020-of-00039.bin +3 -0
- pytorch_model-00021-of-00039.bin +3 -0
- pytorch_model-00022-of-00039.bin +3 -0
- pytorch_model-00023-of-00039.bin +3 -0
- pytorch_model-00024-of-00039.bin +3 -0
- pytorch_model-00025-of-00039.bin +3 -0
- pytorch_model-00026-of-00039.bin +3 -0
- pytorch_model-00027-of-00039.bin +3 -0
- pytorch_model-00028-of-00039.bin +3 -0
- pytorch_model-00029-of-00039.bin +3 -0
- pytorch_model-00030-of-00039.bin +3 -0
- pytorch_model-00031-of-00039.bin +3 -0
- pytorch_model-00032-of-00039.bin +3 -0
- pytorch_model-00033-of-00039.bin +3 -0
- pytorch_model-00034-of-00039.bin +3 -0
- pytorch_model-00035-of-00039.bin +3 -0
- pytorch_model-00036-of-00039.bin +3 -0
- pytorch_model-00037-of-00039.bin +3 -0
- pytorch_model-00038-of-00039.bin +3 -0
- pytorch_model-00039-of-00039.bin +3 -0
- pytorch_model.bin.index.json +330 -0
- special_tokens_map.json +1 -0
- tokenizer.model +3 -0
- tokenizer_config.json +1 -0
config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/karajan/labzone/textgen/alpaca-lora/open_llama_7b_preview_200bt_transformers_weights",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 11008,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 32,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"rms_norm_eps": 1e-06,
|
| 18 |
+
"tie_word_embeddings": false,
|
| 19 |
+
"torch_dtype": "float16",
|
| 20 |
+
"transformers_version": "4.28.1",
|
| 21 |
+
"use_cache": true,
|
| 22 |
+
"vocab_size": 32000
|
| 23 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.28.1"
|
| 7 |
+
}
|
pytorch_model-00001-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81a9b01165a5bf04feaadaef38b566319f997d0c5ff4d2a11f672166de68de38
|
| 3 |
+
size 396364479
|
pytorch_model-00002-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82baa0e29df9372c18641f0d6a18de7d8e4bc102c1659094b0a86a74360199d6
|
| 3 |
+
size 371215393
|
pytorch_model-00003-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b92ddc0ec08253a874aba005922edffa4439a29d9d1f20668c9fb7c2893de46
|
| 3 |
+
size 371215986
|
pytorch_model-00004-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1496e4362f2f73386b77fc1c4a60ab9e0830edd715da36137adc4be747a5a439
|
| 3 |
+
size 371215986
|
pytorch_model-00005-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0b29d102521d50b6324f496d5786967b8b14c870a7e0838afa96b7aad61e472
|
| 3 |
+
size 371215986
|
pytorch_model-00006-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb542a4bee094419082368dc87deef6554f880a579c77686eac856fa8996bce3
|
| 3 |
+
size 314575888
|
pytorch_model-00007-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d09daf1e949d11ef625e7b94836dd777dae7505b549a31d633aa134218a67a3
|
| 3 |
+
size 314592882
|
pytorch_model-00008-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f173b845fe8446eb104820dc27a2e4f05e1a2b665fe361d39e09da7fc175ad25
|
| 3 |
+
size 314592882
|
pytorch_model-00009-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dcf89039f6136558ff443322d724bf0d199be519501ebe7c356e61f3c545456
|
| 3 |
+
size 371215393
|
pytorch_model-00010-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4263bf4a9b9d223e6a44382841f3ebc6c5ee7860df69566e5c69d1a32d7c1335
|
| 3 |
+
size 371215986
|
pytorch_model-00011-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64ac25183d859526bfedfa82142f96e86c898ec54f7619361d517579ca11e556
|
| 3 |
+
size 371215986
|
pytorch_model-00012-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3eac7a8541660eb95a05f3455950f664932aca252b7fb41b3c07c8561fd2450c
|
| 3 |
+
size 371215986
|
pytorch_model-00013-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7752683150b4dd1cdc71638ccf307bef03152a575e533d9d26c9924d1bb5bf5
|
| 3 |
+
size 314575888
|
pytorch_model-00014-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dfc81e9a37c7f476f42e94e8ceb5d7dc9030a10dcc084906aeba2b742c218df
|
| 3 |
+
size 314592882
|
pytorch_model-00015-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:937623fa0388b1f367aeb7cfb934f4c39304369a9af5103150397fe7ed12695c
|
| 3 |
+
size 314592882
|
pytorch_model-00016-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb5360c0acfca433d0fe8b794bac8ab7cc4ba24d444cf5203538d54b622fa2e7
|
| 3 |
+
size 371215393
|
pytorch_model-00017-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a50801a01bf93b40adc6e4fd6b914702e4b936e9c6bb04cbcb94e96f6f029a33
|
| 3 |
+
size 371215986
|
pytorch_model-00018-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5547a7b93e1feab17ccd087ebcd1a5f8e233519a6aef550ead8b90a1ebd47e2
|
| 3 |
+
size 371215986
|
pytorch_model-00019-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa7b3f1487ca3f8db0c56d8e2d13355fb713b5256569ff86c7f06c4680722c92
|
| 3 |
+
size 371215986
|
pytorch_model-00020-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40a4b17afe511d7d408b8a8b712299ee31ff0290890aef55de90751f1372a897
|
| 3 |
+
size 314575888
|
pytorch_model-00021-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0616550fc7ecaf2eb4bbd4ebe5b00dcb5a9f5be1bb08b9c3f4f5956d5e503df8
|
| 3 |
+
size 314592882
|
pytorch_model-00022-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb426dd234ae5f001f8ef89798db374d7932340962f87d886f54b8935a8995d0
|
| 3 |
+
size 314592882
|
pytorch_model-00023-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f392c4fb4b5603e53aae4efdd081637fbb19a86c2589e621c1833a0fbd17a33
|
| 3 |
+
size 371215393
|
pytorch_model-00024-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c83085e6505f05305f757bb9c9bb5d2268826d3910150ee5bde8ede5bf2a23b1
|
| 3 |
+
size 371215986
|
pytorch_model-00025-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f34c696580639fb9f959fb6350153d7e39f7a02f999126fcea97e79fcd2926da
|
| 3 |
+
size 371215986
|
pytorch_model-00026-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d8f7de9bcdacd81b26d98a18a2ba758025815afb192e224676ca9f38f051c54
|
| 3 |
+
size 371215986
|
pytorch_model-00027-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb0130f152666f811e6a647d6b3579cad5f9da2d6540bf2833b9d6c99f399491
|
| 3 |
+
size 314575888
|
pytorch_model-00028-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df86c9e49c0de27c7d124981f98761dca4d0eb6fddb503c0423f26b73d4e8850
|
| 3 |
+
size 314592882
|
pytorch_model-00029-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d7236f00014bd16b038b79868a2549e8a4721354722f8660331492033a89b24
|
| 3 |
+
size 314592882
|
pytorch_model-00030-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b62aeeff3e30b75acfb65fe14127a21b7b89e13afdf8582e5389757e69a0f2e
|
| 3 |
+
size 371215393
|
pytorch_model-00031-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2e30b67cc8e3a7661feb8ea71d17456c19b10f9de3e4367fd90ead17a964a83
|
| 3 |
+
size 371215986
|
pytorch_model-00032-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72aed1ca1ae7d15f878b74cc5fce5351fcb5ccfd7bcb330640916360788b419c
|
| 3 |
+
size 371215986
|
pytorch_model-00033-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2107332e4bc65f0197b4afd184f122387077b34511359fdd2fff60d0a17b3bc8
|
| 3 |
+
size 371215986
|
pytorch_model-00034-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fce04e7d120322a35563443db6225796fbe91924526a20b73d090275dd8917c2
|
| 3 |
+
size 314575888
|
pytorch_model-00035-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7516127f72eb1932b91a829473b110ffe8ef6891a5e8dae02c43a76576061c1
|
| 3 |
+
size 314592882
|
pytorch_model-00036-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42c1b5a7e32d3ddeecb314ec9d0c7654957763942edfa7c3561ed43e5de9c0bb
|
| 3 |
+
size 314592882
|
pytorch_model-00037-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5325b1272cf15bed665e377691d4d053240e36e8ed15fed56489f12d4c99c892
|
| 3 |
+
size 371215393
|
pytorch_model-00038-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0e5d95b451d23141917b99defae6699ec131a9cb705fc4003f3dce1dc83377b
|
| 3 |
+
size 304114977
|
pytorch_model-00039-of-00039.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ac1bf32a1ea644875c20900e8bbc0e75f79794a630d5c70fe71f3624405ba84
|
| 3 |
+
size 262144938
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13476839424
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00039-of-00039.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00039.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00039.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00039.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00039.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00039.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00039.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00039.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00039.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00039.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00039.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00039.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00039.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00039.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00039.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00039.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00039.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00039.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00039.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00039.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00039.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00039.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00014-of-00039.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00013-of-00039.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00013-of-00039.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00014-of-00039.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00014-of-00039.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00013-of-00039.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00013-of-00039.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00013-of-00039.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00039.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00013-of-00039.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00015-of-00039.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00015-of-00039.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00014-of-00039.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00015-of-00039.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00015-of-00039.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00014-of-00039.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00014-of-00039.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00014-of-00039.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00039.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00014-of-00039.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00016-of-00039.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00016-of-00039.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00016-of-00039.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00016-of-00039.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00016-of-00039.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00015-of-00039.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00015-of-00039.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00015-of-00039.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00039.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00015-of-00039.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00017-of-00039.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00017-of-00039.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00017-of-00039.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00017-of-00039.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00017-of-00039.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00016-of-00039.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00017-of-00039.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00016-of-00039.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00039.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00016-of-00039.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00018-of-00039.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00018-of-00039.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00018-of-00039.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00018-of-00039.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00018-of-00039.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00017-of-00039.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00018-of-00039.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00017-of-00039.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00039.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00018-of-00039.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00019-of-00039.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00019-of-00039.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00019-of-00039.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00019-of-00039.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00019-of-00039.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00019-of-00039.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00019-of-00039.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00018-of-00039.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00039.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00019-of-00039.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00021-of-00039.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00020-of-00039.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00020-of-00039.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00021-of-00039.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00021-of-00039.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00020-of-00039.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00020-of-00039.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00020-of-00039.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00039.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00020-of-00039.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00022-of-00039.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00022-of-00039.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00021-of-00039.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00022-of-00039.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00022-of-00039.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00021-of-00039.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00021-of-00039.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00021-of-00039.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00039.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00021-of-00039.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00023-of-00039.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00023-of-00039.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00023-of-00039.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00023-of-00039.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00023-of-00039.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00022-of-00039.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00022-of-00039.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00022-of-00039.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00039.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00022-of-00039.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00024-of-00039.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00024-of-00039.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00024-of-00039.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00024-of-00039.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00024-of-00039.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00023-of-00039.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00024-of-00039.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00023-of-00039.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00039.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00023-of-00039.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00039.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00039.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00039.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00039.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00039.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00039.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00004-of-00039.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00039.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00039.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00039.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00025-of-00039.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00025-of-00039.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00025-of-00039.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00025-of-00039.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00025-of-00039.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00024-of-00039.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00025-of-00039.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00024-of-00039.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00039.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00025-of-00039.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00026-of-00039.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00026-of-00039.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00026-of-00039.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00026-of-00039.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00026-of-00039.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00026-of-00039.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00026-of-00039.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00025-of-00039.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00039.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00026-of-00039.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00028-of-00039.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00027-of-00039.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00027-of-00039.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00028-of-00039.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00028-of-00039.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00027-of-00039.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00027-of-00039.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00027-of-00039.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00039.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00027-of-00039.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00029-of-00039.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00029-of-00039.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00028-of-00039.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00029-of-00039.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00029-of-00039.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00028-of-00039.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00028-of-00039.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00028-of-00039.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00039.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00028-of-00039.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00030-of-00039.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00030-of-00039.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00030-of-00039.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00030-of-00039.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00030-of-00039.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00029-of-00039.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00029-of-00039.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00029-of-00039.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00039.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00029-of-00039.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00031-of-00039.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00031-of-00039.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00031-of-00039.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00031-of-00039.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00031-of-00039.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00030-of-00039.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00031-of-00039.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00030-of-00039.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00039.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00030-of-00039.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00032-of-00039.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00032-of-00039.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00032-of-00039.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00032-of-00039.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00032-of-00039.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00031-of-00039.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00032-of-00039.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00031-of-00039.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00039.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00032-of-00039.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00033-of-00039.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00033-of-00039.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00033-of-00039.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00033-of-00039.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00033-of-00039.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00033-of-00039.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00033-of-00039.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00032-of-00039.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00039.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00033-of-00039.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00035-of-00039.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00034-of-00039.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00034-of-00039.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00035-of-00039.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00035-of-00039.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00034-of-00039.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00034-of-00039.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00034-of-00039.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00039.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00034-of-00039.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00036-of-00039.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00036-of-00039.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00035-of-00039.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00036-of-00039.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00036-of-00039.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00035-of-00039.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00035-of-00039.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00035-of-00039.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00039.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00035-of-00039.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00039.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00039.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00039.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00039.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00039.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00005-of-00039.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00005-of-00039.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00039.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00039.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00005-of-00039.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00037-of-00039.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00037-of-00039.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00037-of-00039.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00037-of-00039.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00037-of-00039.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00036-of-00039.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00036-of-00039.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00036-of-00039.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00036-of-00039.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00036-of-00039.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00038-of-00039.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00038-of-00039.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00038-of-00039.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00038-of-00039.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00038-of-00039.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00037-of-00039.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00038-of-00039.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00037-of-00039.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00038-of-00039.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00037-of-00039.bin",
|
| 268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00039.bin",
|
| 269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00039.bin",
|
| 270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00039.bin",
|
| 271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00039.bin",
|
| 272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00039.bin",
|
| 273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00006-of-00039.bin",
|
| 274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00006-of-00039.bin",
|
| 275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00006-of-00039.bin",
|
| 276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00039.bin",
|
| 277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00006-of-00039.bin",
|
| 278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00039.bin",
|
| 279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00039.bin",
|
| 280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00039.bin",
|
| 281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00039.bin",
|
| 282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00039.bin",
|
| 283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00007-of-00039.bin",
|
| 284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00007-of-00039.bin",
|
| 285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00007-of-00039.bin",
|
| 286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00039.bin",
|
| 287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00007-of-00039.bin",
|
| 288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00009-of-00039.bin",
|
| 289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00009-of-00039.bin",
|
| 290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00039.bin",
|
| 291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00039.bin",
|
| 292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00009-of-00039.bin",
|
| 293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00008-of-00039.bin",
|
| 294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00008-of-00039.bin",
|
| 295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00008-of-00039.bin",
|
| 296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00039.bin",
|
| 297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00008-of-00039.bin",
|
| 298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00010-of-00039.bin",
|
| 299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00010-of-00039.bin",
|
| 300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00039.bin",
|
| 301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00010-of-00039.bin",
|
| 302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00010-of-00039.bin",
|
| 303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00009-of-00039.bin",
|
| 304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00039.bin",
|
| 305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00009-of-00039.bin",
|
| 306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00039.bin",
|
| 307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00009-of-00039.bin",
|
| 308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00011-of-00039.bin",
|
| 309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00011-of-00039.bin",
|
| 310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00011-of-00039.bin",
|
| 311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00011-of-00039.bin",
|
| 312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00011-of-00039.bin",
|
| 313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00010-of-00039.bin",
|
| 314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00039.bin",
|
| 315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00010-of-00039.bin",
|
| 316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00039.bin",
|
| 317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00011-of-00039.bin",
|
| 318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00012-of-00039.bin",
|
| 319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00012-of-00039.bin",
|
| 320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00012-of-00039.bin",
|
| 321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00012-of-00039.bin",
|
| 322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00012-of-00039.bin",
|
| 323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00012-of-00039.bin",
|
| 324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00012-of-00039.bin",
|
| 325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00011-of-00039.bin",
|
| 326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00039.bin",
|
| 327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00012-of-00039.bin",
|
| 328 |
+
"model.norm.weight": "pytorch_model-00038-of-00039.bin"
|
| 329 |
+
}
|
| 330 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc820fc43f4173d6362c16658c409ed423929a807e55a984af96cce1277d39a4
|
| 3 |
+
size 772031
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LlamaTokenizer", "unk_token": ""}
|