初始化项目，由ModelHub XC社区提供模型
Model: mlx-community/Apertus-8B-Instruct-2509-bf16 Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: swiss-ai/Apertus-8B-Instruct-2509
|
||||
pipeline_tag: text-generation
|
||||
library_name: mlx
|
||||
tags:
|
||||
- multilingual
|
||||
- compliant
|
||||
- swiss-ai
|
||||
- apertus
|
||||
- mlx
|
||||
extra_gated_prompt: "### Apertus LLM Acceptable Use Policy \n(1.0 | September 1,\
|
||||
\ 2025)\n\"Agreement\" The Swiss National AI Institute (SNAI) is a partnership between\
|
||||
\ the two Swiss Federal Institutes of Technology, ETH Zurich and EPFL. \n\nBy using\
|
||||
\ the Apertus LLM you agree to indemnify, defend, and hold harmless ETH Zurich and\
|
||||
\ EPFL against any third-party claims arising from your use of Apertus LLM. \n\n\
|
||||
The training data and the Apertus LLM may contain or generate information that directly\
|
||||
\ or indirectly refers to an identifiable individual (Personal Data). You process\
|
||||
\ Personal Data as independent controller in accordance with applicable data protection\
|
||||
\ law. SNAI will regularly provide a file with hash values for download which you\
|
||||
\ can apply as an output filter to your use of our Apertus LLM. The file reflects\
|
||||
\ data protection deletion requests which have been addressed to SNAI as the developer\
|
||||
\ of the Apertus LLM. It allows you to remove Personal Data contained in the model\
|
||||
\ output. We strongly advise downloading and applying this output filter from SNAI\
|
||||
\ every six months following the release of the model. "
|
||||
extra_gated_fields:
|
||||
Your Name: text
|
||||
Country: country
|
||||
Affiliation: text
|
||||
geo: ip_location
|
||||
By clicking Submit below I accept the terms of use: checkbox
|
||||
extra_gated_button_content: Submit
|
||||
---
|
||||
|
||||
# mlx-community/Apertus-8B-Instruct-2509-bf16
|
||||
|
||||
This model [mlx-community/Apertus-8B-Instruct-2509-bf16](https://huggingface.co/mlx-community/Apertus-8B-Instruct-2509-bf16) was
|
||||
converted to MLX format from [swiss-ai/Apertus-8B-Instruct-2509](https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509)
|
||||
using mlx-lm version **0.27.0**.
|
||||
|
||||
## Use with mlx
|
||||
|
||||
```bash
|
||||
pip install mlx-lm
|
||||
```
|
||||
|
||||
```python
|
||||
from mlx_lm import load, generate
|
||||
|
||||
model, tokenizer = load("mlx-community/Apertus-8B-Instruct-2509-bf16")
|
||||
|
||||
prompt = "hello"
|
||||
|
||||
if tokenizer.chat_template is not None:
|
||||
messages = [{"role": "user", "content": prompt}]
|
||||
prompt = tokenizer.apply_chat_template(
|
||||
messages, add_generation_prompt=True
|
||||
)
|
||||
|
||||
response = generate(model, tokenizer, prompt=prompt, verbose=True)
|
||||
```
|
||||
38
config.json
Normal file
38
config.json
Normal file
@@ -0,0 +1,38 @@
|
||||
{
|
||||
"architectures": [
|
||||
"ApertusForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 68,
|
||||
"hidden_act": "xielu",
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 21504,
|
||||
"max_position_embeddings": 65536,
|
||||
"mlp_bias": false,
|
||||
"model_type": "apertus",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 3,
|
||||
"post_norm": false,
|
||||
"qk_norm": true,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3",
|
||||
"type": "llama3"
|
||||
},
|
||||
"rope_theta": 12000000,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.56.0.dev0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
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, 68, 72],
|
||||
"transformers_version": "4.54.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:36fcf8ce7cfbfcfca9273035d9040edffee7f9e1622d29eece61c9fe0ad8ac51
|
||||
size 5259824750
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6bc8ac5913fe0e9b04eed8ece00be709c688d742671a18fd521572bcc9a4df2e
|
||||
size 5234713015
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a796d03b186166f652d38533819cd14518ac6cc45120a811786ffe998ede8d4c
|
||||
size 4538447086
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1fe8663058b35beed5c4408547e2929861d40586e2029c3a6a43aaa75fb5fd48
|
||||
size 1073741951
|
||||
459
model.safetensors.index.json
Normal file
459
model.safetensors.index.json
Normal file
@@ -0,0 +1,459 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16106676480,
|
||||
"total_parameters": 8053338240
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|assistant_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3d5f2074cd9c771f2d3f35a75ea4c86886ac629fa40580128a1f66c9acb58cc0
|
||||
size 17078483
|
||||
8021
tokenizer_config.json
Normal file
8021
tokenizer_config.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user