Upload LlamaForCausalLM
Browse files- config.json +4 -14
- generation_config.json +2 -8
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
config.json
CHANGED
|
@@ -1,21 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"bos_token_id": 128000,
|
| 9 |
-
"eos_token_id":
|
| 10 |
-
128001,
|
| 11 |
-
128008,
|
| 12 |
-
128009
|
| 13 |
-
],
|
| 14 |
"hidden_act": "silu",
|
| 15 |
"hidden_size": 4096,
|
| 16 |
"initializer_range": 0.02,
|
| 17 |
"intermediate_size": 14336,
|
| 18 |
-
"max_position_embeddings":
|
| 19 |
"mlp_bias": false,
|
| 20 |
"model_type": "llama",
|
| 21 |
"num_attention_heads": 32,
|
|
@@ -23,13 +19,7 @@
|
|
| 23 |
"num_key_value_heads": 8,
|
| 24 |
"pretraining_tp": 1,
|
| 25 |
"rms_norm_eps": 1e-05,
|
| 26 |
-
"rope_scaling":
|
| 27 |
-
"factor": 8.0,
|
| 28 |
-
"high_freq_factor": 4.0,
|
| 29 |
-
"low_freq_factor": 1.0,
|
| 30 |
-
"original_max_position_embeddings": 8192,
|
| 31 |
-
"rope_type": "llama3"
|
| 32 |
-
},
|
| 33 |
"rope_theta": 500000.0,
|
| 34 |
"tie_word_embeddings": false,
|
| 35 |
"torch_dtype": "float16",
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "m42-health/Llama3-Med42-8B",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": 128001,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 4096,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 8192,
|
| 15 |
"mlp_bias": false,
|
| 16 |
"model_type": "llama",
|
| 17 |
"num_attention_heads": 32,
|
|
|
|
| 19 |
"num_key_value_heads": 8,
|
| 20 |
"pretraining_tp": 1,
|
| 21 |
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"rope_theta": 500000.0,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "float16",
|
generation_config.json
CHANGED
|
@@ -1,12 +1,6 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"bos_token_id": 128000,
|
| 3 |
-
"
|
| 4 |
-
"eos_token_id": [
|
| 5 |
-
128001,
|
| 6 |
-
128008,
|
| 7 |
-
128009
|
| 8 |
-
],
|
| 9 |
-
"temperature": 0.6,
|
| 10 |
-
"top_p": 0.9,
|
| 11 |
"transformers_version": "4.44.1"
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
"bos_token_id": 128000,
|
| 4 |
+
"eos_token_id": 128001,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"transformers_version": "4.44.1"
|
| 6 |
}
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4976698592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:becc4e486f7dbcefd76ca3a78f9c82f53836b68f9a5e3754144b2fb646e9cef5
|
| 3 |
size 4976698592
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999802616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64334b0f8f24b25fabcc885ecb98459d68d14e72c399637ddf8d2538687c73a3
|
| 3 |
size 4999802616
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915916080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b34e7d72fbccac01dfe6af90ac77c4ccf931fc04a05e6246fe1c8adf44d3c0a3
|
| 3 |
size 4915916080
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1168138808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1140ba1c2adb8546d6c7afe90b5af83f532ce576d35773326b77fc144d3f5c6b
|
| 3 |
size 1168138808
|