Text Generation
Transformers
Safetensors
phi3
torchwright
compiled-transformer
calculator_simple
text-generation-inference
Instructions to use physicsrob/torchwright-calculator-simple-max-digits-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use physicsrob/torchwright-calculator-simple-max-digits-3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="physicsrob/torchwright-calculator-simple-max-digits-3")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("physicsrob/torchwright-calculator-simple-max-digits-3") model = AutoModelForCausalLM.from_pretrained("physicsrob/torchwright-calculator-simple-max-digits-3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use physicsrob/torchwright-calculator-simple-max-digits-3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "physicsrob/torchwright-calculator-simple-max-digits-3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "physicsrob/torchwright-calculator-simple-max-digits-3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/physicsrob/torchwright-calculator-simple-max-digits-3
- SGLang
How to use physicsrob/torchwright-calculator-simple-max-digits-3 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "physicsrob/torchwright-calculator-simple-max-digits-3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "physicsrob/torchwright-calculator-simple-max-digits-3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "physicsrob/torchwright-calculator-simple-max-digits-3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "physicsrob/torchwright-calculator-simple-max-digits-3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use physicsrob/torchwright-calculator-simple-max-digits-3 with Docker Model Runner:
docker model run hf.co/physicsrob/torchwright-calculator-simple-max-digits-3
Upload folder using huggingface_hub
Browse files- README.md +2 -2
- config.json +4 -4
- model-00001-of-00028.safetensors +2 -2
- model-00002-of-00028.safetensors +2 -2
- model-00003-of-00028.safetensors +2 -2
- model-00004-of-00028.safetensors +2 -2
- model-00005-of-00028.safetensors +2 -2
- model-00006-of-00028.safetensors +2 -2
- model-00007-of-00028.safetensors +2 -2
- model-00008-of-00028.safetensors +2 -2
- model-00009-of-00028.safetensors +2 -2
- model-00010-of-00028.safetensors +2 -2
- model-00011-of-00028.safetensors +2 -2
- model-00012-of-00028.safetensors +2 -2
- model-00013-of-00028.safetensors +2 -2
- model-00014-of-00028.safetensors +2 -2
- model-00015-of-00028.safetensors +2 -2
- model-00016-of-00028.safetensors +2 -2
- model-00017-of-00028.safetensors +2 -2
- model-00018-of-00028.safetensors +2 -2
- model-00019-of-00028.safetensors +2 -2
- model-00020-of-00028.safetensors +2 -2
- model-00021-of-00028.safetensors +2 -2
- model-00022-of-00028.safetensors +2 -2
- model-00023-of-00028.safetensors +2 -2
- model-00024-of-00028.safetensors +2 -2
- model-00025-of-00028.safetensors +2 -2
- model-00026-of-00028.safetensors +2 -2
- model-00027-of-00028.safetensors +2 -2
- model-00028-of-00028.safetensors +2 -2
- model.safetensors.index.json +1 -1
README.md
CHANGED
|
@@ -69,8 +69,8 @@ exhaustive verification of every allowed expression.
|
|
| 69 |
|
| 70 |
## Size
|
| 71 |
|
| 72 |
-
The checkpoint stores
|
| 73 |
-
|
| 74 |
exactly zero: the vast majority of the model is unused canvas, so size reflects
|
| 75 |
the compile geometry rather than stored knowledge.
|
| 76 |
|
|
|
|
| 69 |
|
| 70 |
## Size
|
| 71 |
|
| 72 |
+
The checkpoint stores 4.08 GB of dense fp32 weights (1,019,639,808 entries) at compile width d=2048.
|
| 73 |
+
99.98% of those entries are
|
| 74 |
exactly zero: the vast majority of the model is unused canvas, so size reflects
|
| 75 |
the compile geometry rather than stored knowledge.
|
| 76 |
|
config.json
CHANGED
|
@@ -8,14 +8,14 @@
|
|
| 8 |
"eos_token_id": 16,
|
| 9 |
"head_dim": 64,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
-
"hidden_size":
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size":
|
| 14 |
"max_position_embeddings": 512,
|
| 15 |
"model_type": "phi3",
|
| 16 |
-
"num_attention_heads":
|
| 17 |
"num_hidden_layers": 27,
|
| 18 |
-
"num_key_value_heads":
|
| 19 |
"original_max_position_embeddings": 4096,
|
| 20 |
"pad_token_id": null,
|
| 21 |
"resid_pdrop": 0.0,
|
|
|
|
| 8 |
"eos_token_id": 16,
|
| 9 |
"head_dim": 64,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3415,
|
| 14 |
"max_position_embeddings": 512,
|
| 15 |
"model_type": "phi3",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
"num_hidden_layers": 27,
|
| 18 |
+
"num_key_value_heads": 32,
|
| 19 |
"original_max_position_embeddings": 4096,
|
| 20 |
"pad_token_id": null,
|
| 21 |
"resid_pdrop": 0.0,
|
model-00001-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:824b74c24d3e2009bf1746b4960fcd4fe27c2adb9aae1afc04173f5776de3210
|
| 3 |
+
size 151036360
|
model-00002-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1377379e03d5d0dffa320408c70f6ff508827d1ac8a5e7664bcf1771a95b573
|
| 3 |
+
size 151036360
|
model-00003-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86c478de5832354dd97a0b3199e70b00894b985076a625ab32a3d147f4ced288
|
| 3 |
+
size 151036360
|
model-00004-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b37dd309e6bf011f920ff002f600043ce018d8f83347a9a943503445902eb8ff
|
| 3 |
+
size 151036360
|
model-00005-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:341f54300d6928cdcdb6346deb4efc9ef3250950d5c3a4df9cf53fc2dbf65d81
|
| 3 |
+
size 151036360
|
model-00006-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58d744c6e59ae00b335045442594ab07568150a3ba42bb449a3644e04b19d471
|
| 3 |
+
size 151036360
|
model-00007-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ebb2b437c55a36a23b628682cb14394d7cf7bc0d4bf7a22474ada367c20ac1a
|
| 3 |
+
size 151036360
|
model-00008-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25eb7aca11722819ef664fbfcf1258b2af29d5cbc6e9b27ee98d7a5052c38c4d
|
| 3 |
+
size 151036360
|
model-00009-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d872c7361d628b8ca0164ba398eb83e142837fae34b23b4c3a5aeb0c5eebba0
|
| 3 |
+
size 151036360
|
model-00010-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75130f96bdb2119393c6d5de6a936be72e3eb619f8a8f662f164d9857c4661ba
|
| 3 |
+
size 151036360
|
model-00011-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b22f70402c83c6192425ee7aae158b70207d049b0e59a00d9f2c169000110710
|
| 3 |
+
size 151036360
|
model-00012-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69b0ab8122e3c304f71276cec78469b71c31bc73bbdbbe73c1f5d2ec89509ace
|
| 3 |
+
size 151036360
|
model-00013-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c90f23ad6f7cd30d4a59a568a840bac394e660a882a4c9460d1ef36c2bc749af
|
| 3 |
+
size 151036360
|
model-00014-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5a0b3d0572e02d147f25fc6e0e5f7106ef727e12af01592e45d467eeed4ef22
|
| 3 |
+
size 151036360
|
model-00015-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d469d1857a90fc09a347dfd4857e8a9de3ca959ac81e14c61e768431e2f0888
|
| 3 |
+
size 151036360
|
model-00016-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f56a50558b2b7f67e4d4b7515e3876186d03fd40a46caecf8e92744ae43ae269
|
| 3 |
+
size 151036360
|
model-00017-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60c66b57f8ab4275a357c615f414c6c52a9c3dce4d0829f2db96d857c7b6fe21
|
| 3 |
+
size 151036360
|
model-00018-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2a43d94976176b122b783a9d135e200b510c26ad62602499ba6d8b18e44a86d
|
| 3 |
+
size 151036360
|
model-00019-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb61c0f0ed417db14506ff3e31b697d7928f22edf8397391991938ec452c328c
|
| 3 |
+
size 151036360
|
model-00020-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdbd23c8004d6cb0e3b6e55d58496993254c6a2e73b79709f8d50d019691ed23
|
| 3 |
+
size 151036360
|
model-00021-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fc1a31b0b50956efc0b49762e036bbe16f8567097651e15cf6fef4cdf193341
|
| 3 |
+
size 151036360
|
model-00022-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6925ac3c1547dba03c096dbffee4fcb67f288f0afe306fdd95a1a369a01af17f
|
| 3 |
+
size 151036360
|
model-00023-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0475c2f01c6ac7a747f543600d0b975f70d0d75de2d9a3c22daed96cf728b13b
|
| 3 |
+
size 151036360
|
model-00024-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc573f07e3980e2d2d20785b09c6c052ba2fb31a6fab7ba3ebce99bdc258b284
|
| 3 |
+
size 151036360
|
model-00025-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2897412382107263d5a40c693fdb4949945f241917a6abe59872fb036a494216
|
| 3 |
+
size 151036360
|
model-00026-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df10f9b1f9861bf35d5b3619b89071cb36dc92e60330e0ed4f2c79efdc56a211
|
| 3 |
+
size 151036360
|
model-00027-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4a6244adf7365b7b0effe221c8f6ec40b3be16abe1319105178f61dabfc69de
|
| 3 |
+
size 151036360
|
model-00028-of-00028.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:baf7b350ab14c96a2cead93d980505b1818de5321be08672a3bf979d62eee141
|
| 3 |
+
size 595792
|
model.safetensors.index.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"metadata": {"total_size": 16142598144}, "weight_map": {"model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00028.safetensors", "model.layers.1.self_attn.qkv_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.mlp.gate_up_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.qkv_proj.weight": "model-00003-of-00028.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.2.mlp.gate_up_proj.weight": "model-00003-of-00028.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.qkv_proj.weight": "model-00004-of-00028.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.3.mlp.gate_up_proj.weight": "model-00004-of-00028.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.qkv_proj.weight": "model-00005-of-00028.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.4.mlp.gate_up_proj.weight": "model-00005-of-00028.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.qkv_proj.weight": "model-00006-of-00028.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.5.mlp.gate_up_proj.weight": "model-00006-of-00028.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.qkv_proj.weight": "model-00007-of-00028.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", "model.layers.6.mlp.gate_up_proj.weight": "model-00007-of-00028.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.qkv_proj.weight": "model-00008-of-00028.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.7.mlp.gate_up_proj.weight": "model-00008-of-00028.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.qkv_proj.weight": "model-00009-of-00028.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.8.mlp.gate_up_proj.weight": "model-00009-of-00028.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00028.safetensors", "model.layers.9.self_attn.qkv_proj.weight": "model-00010-of-00028.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.9.mlp.gate_up_proj.weight": "model-00010-of-00028.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00010-of-00028.safetensors", "model.layers.10.self_attn.qkv_proj.weight": "model-00011-of-00028.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", "model.layers.10.mlp.gate_up_proj.weight": "model-00011-of-00028.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00011-of-00028.safetensors", "model.layers.11.self_attn.qkv_proj.weight": "model-00012-of-00028.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.11.mlp.gate_up_proj.weight": "model-00012-of-00028.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00012-of-00028.safetensors", "model.layers.12.self_attn.qkv_proj.weight": "model-00013-of-00028.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.12.mlp.gate_up_proj.weight": "model-00013-of-00028.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00013-of-00028.safetensors", "model.layers.13.self_attn.qkv_proj.weight": "model-00014-of-00028.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.13.mlp.gate_up_proj.weight": "model-00014-of-00028.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00014-of-00028.safetensors", "model.layers.14.self_attn.qkv_proj.weight": "model-00015-of-00028.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.14.mlp.gate_up_proj.weight": "model-00015-of-00028.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00015-of-00028.safetensors", "model.layers.15.self_attn.qkv_proj.weight": "model-00016-of-00028.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.15.mlp.gate_up_proj.weight": "model-00016-of-00028.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00016-of-00028.safetensors", "model.layers.16.self_attn.qkv_proj.weight": "model-00017-of-00028.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.16.mlp.gate_up_proj.weight": "model-00017-of-00028.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00017-of-00028.safetensors", "model.layers.17.self_attn.qkv_proj.weight": "model-00018-of-00028.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.17.mlp.gate_up_proj.weight": "model-00018-of-00028.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00018-of-00028.safetensors", "model.layers.18.self_attn.qkv_proj.weight": "model-00019-of-00028.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", "model.layers.18.mlp.gate_up_proj.weight": "model-00019-of-00028.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00019-of-00028.safetensors", "model.layers.19.self_attn.qkv_proj.weight": "model-00020-of-00028.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.19.mlp.gate_up_proj.weight": "model-00020-of-00028.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00020-of-00028.safetensors", "model.layers.20.self_attn.qkv_proj.weight": "model-00021-of-00028.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.20.mlp.gate_up_proj.weight": "model-00021-of-00028.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00021-of-00028.safetensors", "model.layers.21.self_attn.qkv_proj.weight": "model-00022-of-00028.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.21.mlp.gate_up_proj.weight": "model-00022-of-00028.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00022-of-00028.safetensors", "model.layers.22.self_attn.qkv_proj.weight": "model-00023-of-00028.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", "model.layers.22.mlp.gate_up_proj.weight": "model-00023-of-00028.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00023-of-00028.safetensors", "model.layers.23.self_attn.qkv_proj.weight": "model-00024-of-00028.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.23.mlp.gate_up_proj.weight": "model-00024-of-00028.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00024-of-00028.safetensors", "model.layers.24.self_attn.qkv_proj.weight": "model-00025-of-00028.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.24.mlp.gate_up_proj.weight": "model-00025-of-00028.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00025-of-00028.safetensors", "model.layers.25.self_attn.qkv_proj.weight": "model-00026-of-00028.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.25.mlp.gate_up_proj.weight": "model-00026-of-00028.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00026-of-00028.safetensors", "model.layers.26.self_attn.qkv_proj.weight": "model-00027-of-00028.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.26.mlp.gate_up_proj.weight": "model-00027-of-00028.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00027-of-00028.safetensors", "model.embed_tokens.weight": "model-00028-of-00028.safetensors", "model.norm.weight": "model-00028-of-00028.safetensors", "model.layers.0.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.1.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.2.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.3.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.4.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.5.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.6.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.7.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.8.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.10.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.11.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.12.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.13.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.14.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.15.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.16.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.17.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.18.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.19.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.20.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.21.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.22.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.23.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.24.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.25.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.26.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00028-of-00028.safetensors"}}
|
|
|
|
| 1 |
+
{"metadata": {"total_size": 4078559232}, "weight_map": {"model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00028.safetensors", "model.layers.1.self_attn.qkv_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.mlp.gate_up_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.qkv_proj.weight": "model-00003-of-00028.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.2.mlp.gate_up_proj.weight": "model-00003-of-00028.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.qkv_proj.weight": "model-00004-of-00028.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.3.mlp.gate_up_proj.weight": "model-00004-of-00028.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.qkv_proj.weight": "model-00005-of-00028.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.4.mlp.gate_up_proj.weight": "model-00005-of-00028.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.qkv_proj.weight": "model-00006-of-00028.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.5.mlp.gate_up_proj.weight": "model-00006-of-00028.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.qkv_proj.weight": "model-00007-of-00028.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", "model.layers.6.mlp.gate_up_proj.weight": "model-00007-of-00028.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.qkv_proj.weight": "model-00008-of-00028.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.7.mlp.gate_up_proj.weight": "model-00008-of-00028.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.qkv_proj.weight": "model-00009-of-00028.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.8.mlp.gate_up_proj.weight": "model-00009-of-00028.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00028.safetensors", "model.layers.9.self_attn.qkv_proj.weight": "model-00010-of-00028.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.9.mlp.gate_up_proj.weight": "model-00010-of-00028.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00010-of-00028.safetensors", "model.layers.10.self_attn.qkv_proj.weight": "model-00011-of-00028.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", "model.layers.10.mlp.gate_up_proj.weight": "model-00011-of-00028.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00011-of-00028.safetensors", "model.layers.11.self_attn.qkv_proj.weight": "model-00012-of-00028.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.11.mlp.gate_up_proj.weight": "model-00012-of-00028.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00012-of-00028.safetensors", "model.layers.12.self_attn.qkv_proj.weight": "model-00013-of-00028.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.12.mlp.gate_up_proj.weight": "model-00013-of-00028.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00013-of-00028.safetensors", "model.layers.13.self_attn.qkv_proj.weight": "model-00014-of-00028.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.13.mlp.gate_up_proj.weight": "model-00014-of-00028.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00014-of-00028.safetensors", "model.layers.14.self_attn.qkv_proj.weight": "model-00015-of-00028.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.14.mlp.gate_up_proj.weight": "model-00015-of-00028.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00015-of-00028.safetensors", "model.layers.15.self_attn.qkv_proj.weight": "model-00016-of-00028.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.15.mlp.gate_up_proj.weight": "model-00016-of-00028.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00016-of-00028.safetensors", "model.layers.16.self_attn.qkv_proj.weight": "model-00017-of-00028.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.16.mlp.gate_up_proj.weight": "model-00017-of-00028.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00017-of-00028.safetensors", "model.layers.17.self_attn.qkv_proj.weight": "model-00018-of-00028.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.17.mlp.gate_up_proj.weight": "model-00018-of-00028.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00018-of-00028.safetensors", "model.layers.18.self_attn.qkv_proj.weight": "model-00019-of-00028.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", "model.layers.18.mlp.gate_up_proj.weight": "model-00019-of-00028.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00019-of-00028.safetensors", "model.layers.19.self_attn.qkv_proj.weight": "model-00020-of-00028.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.19.mlp.gate_up_proj.weight": "model-00020-of-00028.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00020-of-00028.safetensors", "model.layers.20.self_attn.qkv_proj.weight": "model-00021-of-00028.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.20.mlp.gate_up_proj.weight": "model-00021-of-00028.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00021-of-00028.safetensors", "model.layers.21.self_attn.qkv_proj.weight": "model-00022-of-00028.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.21.mlp.gate_up_proj.weight": "model-00022-of-00028.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00022-of-00028.safetensors", "model.layers.22.self_attn.qkv_proj.weight": "model-00023-of-00028.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", "model.layers.22.mlp.gate_up_proj.weight": "model-00023-of-00028.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00023-of-00028.safetensors", "model.layers.23.self_attn.qkv_proj.weight": "model-00024-of-00028.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.23.mlp.gate_up_proj.weight": "model-00024-of-00028.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00024-of-00028.safetensors", "model.layers.24.self_attn.qkv_proj.weight": "model-00025-of-00028.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.24.mlp.gate_up_proj.weight": "model-00025-of-00028.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00025-of-00028.safetensors", "model.layers.25.self_attn.qkv_proj.weight": "model-00026-of-00028.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.25.mlp.gate_up_proj.weight": "model-00026-of-00028.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00026-of-00028.safetensors", "model.layers.26.self_attn.qkv_proj.weight": "model-00027-of-00028.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.26.mlp.gate_up_proj.weight": "model-00027-of-00028.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00027-of-00028.safetensors", "model.embed_tokens.weight": "model-00028-of-00028.safetensors", "model.norm.weight": "model-00028-of-00028.safetensors", "model.layers.0.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.1.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.2.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.3.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.4.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.5.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.6.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.7.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.8.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.10.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.11.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.12.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.13.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.14.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.15.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.16.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.17.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.18.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.19.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.20.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.21.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.22.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.23.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.24.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.25.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.26.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00028-of-00028.safetensors"}}
|