初始化项目，由ModelHub XC社区提供模型
Model: filipealmeida/Mistral-7B-Instruct-v0.1-sharded Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
54
README.md
Normal file
54
README.md
Normal file
@@ -0,0 +1,54 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- finetuned
|
||||
---
|
||||
|
||||
# Sharded version of Mistral-7B-Instruct-v0.1
|
||||
|
||||
This is the sharded version of Mistral-7B-Instruct-v0.1 so you can use it when you have limited CPU memory
|
||||
|
||||
# Model Card for Mistral-7B-Instruct-v0.1
|
||||
|
||||
The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) generative text model using a variety of publicly available conversation datasets.
|
||||
|
||||
For full details of this model please read our [release blog post](https://mistral.ai/news/announcing-mistral-7b/)
|
||||
|
||||
## Instruction format
|
||||
|
||||
In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[\INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
|
||||
|
||||
E.g.
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
device = "cuda" # the device to load the model onto
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
|
||||
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
|
||||
|
||||
text = "<s>[INST] What is your favourite condiment? [/INST]"
|
||||
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
|
||||
"[INST] Do you have mayonnaise recipes? [/INST]"
|
||||
|
||||
encodeds = tokenizer(text, return_tensors="pt", add_special_tokens=False)
|
||||
|
||||
model_inputs = encodeds.to(device)
|
||||
model.to(device)
|
||||
|
||||
generated_ids = model.generate(**model_inputs, max_new_tokens=1000, do_sample=True)
|
||||
decoded = tokenizer.batch_decode(generated_ids)
|
||||
print(decoded[0])
|
||||
```
|
||||
|
||||
## Model Architecture
|
||||
This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:
|
||||
- Grouped-Query Attention
|
||||
- Sliding-Window Attention
|
||||
- Byte-fallback BPE tokenizer
|
||||
|
||||
## The Mistral AI Team
|
||||
|
||||
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.33.3",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.33.3"
|
||||
}
|
||||
3
pytorch_model-00001-of-00008.bin
Normal file
3
pytorch_model-00001-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a76ff874b5c509a20c67fd50ccb6d2ae9579dd86b1d20dbefdeca8ea7e420e18
|
||||
size 1889594894
|
||||
3
pytorch_model-00002-of-00008.bin
Normal file
3
pytorch_model-00002-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3591ef10f9685b7e60d4ff497e80d0e153352459a7e5e7cd76a020b95d5c196d
|
||||
size 1946253808
|
||||
3
pytorch_model-00003-of-00008.bin
Normal file
3
pytorch_model-00003-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c983fb98b2f1320679343cced7e32de8d5c70b81b68274e8b0ecafb0217a0112
|
||||
size 1979790166
|
||||
3
pytorch_model-00004-of-00008.bin
Normal file
3
pytorch_model-00004-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0461e62f3dd317fcdd22629073b1fe7d748774b0b8b530f17d19763cac3fab41
|
||||
size 1946253872
|
||||
3
pytorch_model-00005-of-00008.bin
Normal file
3
pytorch_model-00005-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f5bcdf2e7a546d072ea2194c4368955c327192912de12a8058fdc2efc4be7c59
|
||||
size 1979790166
|
||||
3
pytorch_model-00006-of-00008.bin
Normal file
3
pytorch_model-00006-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2f6e6e30541ae03c10c72e126f05314e277a08fbd6cbb91f4c2726b0426c9aa1
|
||||
size 1946253872
|
||||
3
pytorch_model-00007-of-00008.bin
Normal file
3
pytorch_model-00007-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d5b5ddedc1d981b30ae41c62191077f7e04b6d74395596f23996ac6f73194efd
|
||||
size 1979790166
|
||||
3
pytorch_model-00008-of-00008.bin
Normal file
3
pytorch_model-00008-of-00008.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:28759eed2fdfa5eb7ebfb91185471457813040991c13ddbde6f71a30cb0ff7f6
|
||||
size 815838502
|
||||
298
pytorch_model.bin.index.json
Normal file
298
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14483464192
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
|
||||
"model.norm.weight": "pytorch_model-00008-of-00008.bin"
|
||||
}
|
||||
}
|
||||
5
special_tokens_map.json
Normal file
5
special_tokens_map.json
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
91122
tokenizer.json
Normal file
91122
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
43
tokenizer_config.json
Normal file
43
tokenizer_config.json
Normal file
@@ -0,0 +1,43 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in New Issue
Block a user