Transformers
Safetensors
llama
speculative-decoding
eagle3
specforge
sglang
qwen3
draft-model
sharegpt
sliding-window-512
text-generation-inference
Instructions to use huluhuluu/qwen3-4b-instruct-2507-eagle3-sharegpt-sw512-epoch2-step60000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huluhuluu/qwen3-4b-instruct-2507-eagle3-sharegpt-sw512-epoch2-step60000 with Transformers:
# Load model directly from transformers import AutoTokenizer, LlamaForCausalLMEagle3 tokenizer = AutoTokenizer.from_pretrained("huluhuluu/qwen3-4b-instruct-2507-eagle3-sharegpt-sw512-epoch2-step60000") model = LlamaForCausalLMEagle3.from_pretrained("huluhuluu/qwen3-4b-instruct-2507-eagle3-sharegpt-sw512-epoch2-step60000", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Archive epoch_2_step_60000
Browse files- config.json +33 -0
- model.safetensors +3 -0
- training_state.pt +3 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLMEagle3"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"draft_vocab_size": 32000,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 151645,
|
| 11 |
+
"head_dim": 80,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 2560,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 9728,
|
| 16 |
+
"max_position_embeddings": 262144,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"model_type": "llama",
|
| 19 |
+
"num_attention_heads": 32,
|
| 20 |
+
"num_hidden_layers": 1,
|
| 21 |
+
"num_key_value_heads": 8,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"rms_norm_eps": 1e-06,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000.0,
|
| 27 |
+
"sliding_window": 512,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"transformers_version": "4.57.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"use_sliding_window": true,
|
| 32 |
+
"vocab_size": 151936
|
| 33 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15d6215c13bae092301cfb52be420384df88e4f3a8aa0001060bf1e4c74ca6eb
|
| 3 |
+
size 405442400
|
training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ff1abcac122963865bc9e96c667ee2dad7b48c6600c95b3e1d541a570c16ce0
|
| 3 |
+
size 4311
|