初始化项目，由ModelHub XC社区提供模型
Model: mlx-community/ether0-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
|
||||
43
README.md
Normal file
43
README.md
Normal file
@@ -0,0 +1,43 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
base_model: futurehouse/ether0
|
||||
datasets:
|
||||
- futurehouse/ether0-benchmark
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- smiles
|
||||
- chemistry
|
||||
- reasoning
|
||||
- mlx
|
||||
library_name: mlx
|
||||
---
|
||||
|
||||
# mlx-community/ether0-bf16
|
||||
|
||||
This model [mlx-community/ether0-bf16](https://huggingface.co/mlx-community/ether0-bf16) was
|
||||
converted to MLX format from [futurehouse/ether0](https://huggingface.co/futurehouse/ether0)
|
||||
using mlx-lm version **0.25.0**.
|
||||
|
||||
## Use with mlx
|
||||
|
||||
```bash
|
||||
pip install mlx-lm
|
||||
```
|
||||
|
||||
```python
|
||||
from mlx_lm import load, generate
|
||||
|
||||
model, tokenizer = load("mlx-community/ether0-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)
|
||||
```
|
||||
22
chat_template.jinja
Normal file
22
chat_template.jinja
Normal file
@@ -0,0 +1,22 @@
|
||||
{%- set default_system_message = "You are a scientific reasoning AI assistant." %}
|
||||
{{- bos_token }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{%- set system_message = messages[0]['content'] %}
|
||||
{%- set loop_messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set system_message = default_system_message %}
|
||||
{%- set loop_messages = messages %}
|
||||
{%- endif %}
|
||||
{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
|
||||
|
||||
{%- for message in loop_messages %}
|
||||
{%- if message['role'] == 'user' %}
|
||||
{{- '[INST]' + message['content'] + '[/INST]' }}
|
||||
{%- elif message['role'] == 'system' %}
|
||||
{{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
|
||||
{%- elif message['role'] == 'assistant' %}
|
||||
{{- message['content'] + eos_token }}
|
||||
{%- else %}
|
||||
{{- raise_exception("Only user, system and assistant roles are supported!") }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 32768,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 100000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.49.0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 131136
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"temperature": 0.15,
|
||||
"transformers_version": "4.49.0"
|
||||
}
|
||||
3
model-00001-of-00019.safetensors
Normal file
3
model-00001-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fbb676c873b996d3c915ff43282a57b0c18db658a6badef8977114c1ddabf822
|
||||
size 5118404184
|
||||
3
model-00002-of-00019.safetensors
Normal file
3
model-00002-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:75883e30c52bf195771834339dcf38fbdb4bbc2ae8e93227ab6ceba4275cc437
|
||||
size 5117135002
|
||||
3
model-00003-of-00019.safetensors
Normal file
3
model-00003-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8e726b7b59a2308e2c947ef63e9159d95462aba47a16d84163c332850fa26469
|
||||
size 5117135000
|
||||
3
model-00004-of-00019.safetensors
Normal file
3
model-00004-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ceb6cd74ee0cd2c26d5d633a6aa94dd31bdd51a13e9534d39578f8fcf8b12300
|
||||
size 5326891857
|
||||
3
model-00005-of-00019.safetensors
Normal file
3
model-00005-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2eabc6e121f59252c9cbcb9314a11956d193309277255034b41bb4eeecfb787e
|
||||
size 5117135005
|
||||
3
model-00006-of-00019.safetensors
Normal file
3
model-00006-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bf7abf4e8a0b877b6148003fc4695945ee9180e75be89e8872abdc2a8d063cdf
|
||||
size 5117135023
|
||||
3
model-00007-of-00019.safetensors
Normal file
3
model-00007-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:64ee19a5dab3fa1458f78d5a251839c567446fdb38824ef15597dd908be61104
|
||||
size 5326891870
|
||||
3
model-00008-of-00019.safetensors
Normal file
3
model-00008-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:639f28d15bf076561fa166d47f002b4eb1af99faaa4f3c7fef168b204df14f8c
|
||||
size 5117135017
|
||||
3
model-00009-of-00019.safetensors
Normal file
3
model-00009-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fe326990b0b31ff4a98828a067a137b0d97d80b5a73b4ebe88ced12a0fb9aeae
|
||||
size 5117135029
|
||||
3
model-00010-of-00019.safetensors
Normal file
3
model-00010-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9175160fbc391d2be0e318c9a37f4718d1bcc51ced2ed45639bc9bc79b5b491e
|
||||
size 5326891868
|
||||
3
model-00011-of-00019.safetensors
Normal file
3
model-00011-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a1782388d2e030000798040ce689602b0391d6ae35acc157a4d36c8f86e689ad
|
||||
size 5117135011
|
||||
3
model-00012-of-00019.safetensors
Normal file
3
model-00012-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2557b4315f632b2f9d6a3dc1dbdcf2cc796a4dc834bac77cace527f7b3dbc582
|
||||
size 5117135017
|
||||
3
model-00013-of-00019.safetensors
Normal file
3
model-00013-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:438e43e7afc9603fab9c9a9256d194f94ec212e410bb6599e0b1e55a30b73735
|
||||
size 5326891872
|
||||
3
model-00014-of-00019.safetensors
Normal file
3
model-00014-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f60ab91a325a2e9857d9b44f810984ccc6439e24df4b94e3610645ba04e13414
|
||||
size 5117135013
|
||||
3
model-00015-of-00019.safetensors
Normal file
3
model-00015-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bd73334ebecfc08d2d3f77d7f3351072e6602c8dccc07b30a92db9141f7495f9
|
||||
size 5117135019
|
||||
3
model-00016-of-00019.safetensors
Normal file
3
model-00016-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:de11d806d95c085d4fb0208bb5a97af20af344b93a820bfe4af1dd974c7a9743
|
||||
size 5326891872
|
||||
3
model-00017-of-00019.safetensors
Normal file
3
model-00017-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d4f31a884af13ffbec059ef91a10b0a8a6bdf2bbcaafa45455fc7a831d0041cb
|
||||
size 5117135023
|
||||
3
model-00018-of-00019.safetensors
Normal file
3
model-00018-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:29aa06b64cf19580cd1edfcd67d64725ddf3a744b0f407fc6caeda8e912899cf
|
||||
size 3565262397
|
||||
3
model-00019-of-00019.safetensors
Normal file
3
model-00019-of-00019.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b7e1915a0d61fbca0bfa30e0d5f517a0a1b27b2b272b0d85a34d1a2429b4901e
|
||||
size 2685665406
|
||||
371
model.safetensors.index.json
Normal file
371
model.safetensors.index.json
Normal file
@@ -0,0 +1,371 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 94292234240,
|
||||
"total_parameters": 23573058560
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00019-of-00019.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00019.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00006-of-00019.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00007-of-00019.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00008-of-00019.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00009-of-00019.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00010-of-00019.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00011-of-00019.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00012-of-00019.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00013-of-00019.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00019.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00014-of-00019.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00015-of-00019.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00016-of-00019.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00018-of-00019.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00018-of-00019.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00018-of-00019.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00018-of-00019.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00017-of-00019.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00018-of-00019.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00018-of-00019.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00018-of-00019.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00018-of-00019.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00018-of-00019.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00018-of-00019.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00018-of-00019.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00018-of-00019.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00018-of-00019.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00019.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00019.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00019.safetensors",
|
||||
"model.norm.weight": "model-00018-of-00019.safetensors"
|
||||
}
|
||||
}
|
||||
1025
special_tokens_map.json
Normal file
1025
special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6396233c0e3e593eb1c4b2dc2e4ec1a8bdb88bf7747c36175b14011b95125508
|
||||
size 17078803
|
||||
9050
tokenizer_config.json
Normal file
9050
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user