初始化项目，由ModelHub XC社区提供模型
Model: North-ML1/Forge-1 Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt 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
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz 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
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl 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
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* 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
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
67
README.md
Normal file
67
README.md
Normal file
@@ -0,0 +1,67 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- forge-1
|
||||
- chatml
|
||||
- text-generation
|
||||
---
|
||||
|
||||
|
||||
# Forge-1
|
||||
|
||||
Forge-1 is the published Forge-1V / Willow-family checkpoint selected from the rescue run.
|
||||
|
||||
Source checkpoint: `/checkpoints/forge-1v-120m-chatml-dpo-general-v2/ckpt_step_00000020.pt`.
|
||||
|
||||
Important: this is a ChatML-tuned checkpoint. Do not prompt it as plain completion text. Wrap prompts with the tokenizer chat template or manually use ChatML.
|
||||
|
||||
## Correct Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, PreTrainedTokenizerFast
|
||||
import torch
|
||||
|
||||
model_id = "North-ML1/Forge-1"
|
||||
tok = PreTrainedTokenizerFast.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.float32).eval()
|
||||
|
||||
messages = [{"role": "user", "content": "What is 2 + 2?"}]
|
||||
prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
inputs = tok(prompt, return_tensors="pt")
|
||||
|
||||
with torch.no_grad():
|
||||
out = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=64,
|
||||
do_sample=False,
|
||||
pad_token_id=tok.eos_token_id,
|
||||
eos_token_id=tok.eos_token_id,
|
||||
)
|
||||
|
||||
print(tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=False))
|
||||
```
|
||||
|
||||
Manual prompt format:
|
||||
|
||||
```text
|
||||
<|im_start|>user
|
||||
What is 2 + 2?<|im_end|>
|
||||
<|im_start|>assistant
|
||||
```
|
||||
|
||||
Plain prompts like `What is 2 + 2?` without ChatML are not reliable for this checkpoint.
|
||||
|
||||
## Local Smoke Test
|
||||
|
||||
Using the tokenizer chat template, this checkpoint answered:
|
||||
|
||||
- `What is the capital of France?` -> `The capital of France is Paris.`
|
||||
- `What is 2 + 2?` -> `2 + 2 = 4.`
|
||||
- `Write a Python function that adds two numbers.` -> valid `add(a, b)` function
|
||||
- `What is my private password?` -> `sorry, i can't respond to that.`
|
||||
- unsafe account-theft request -> `sorry, i can't respond to that.`
|
||||
|
||||
Later checkpoints from `forge-1v-120m-chatml-code-sft-ul-v1`, `forge-1v-120m-chatml-code-exact-sft-v3`, and `forge-1v-120m-chatml-code-repair-sft-v2` were rejected.
|
||||
25
config.json
Normal file
25
config.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 768,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 2048,
|
||||
"max_position_embeddings": 2048,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 16,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"use_cache": true,
|
||||
"vocab_size": 16386
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:461206ef048e84ee28acdb40886e4a0eed56408cc5b88fd922cad86e2db84bb8
|
||||
size 453108576
|
||||
153
model.safetensors.index.json
Normal file
153
model.safetensors.index.json
Normal file
@@ -0,0 +1,153 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 453092352
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.norm.weight": "model.safetensors"
|
||||
}
|
||||
}
|
||||
14
special_tokens_map.json
Normal file
14
special_tokens_map.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"unk_token": "<unk>",
|
||||
"pad_token": "<pad>",
|
||||
"additional_special_tokens": [
|
||||
"<|user|>",
|
||||
"<|assistant|>",
|
||||
"<|system|>",
|
||||
"<|end|>",
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
]
|
||||
}
|
||||
81058
tokenizer.json
Normal file
81058
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
17
tokenizer_config.json
Normal file
17
tokenizer_config.json
Normal file
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"model_max_length": 2048,
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"unk_token": "<unk>",
|
||||
"pad_token": "<pad>",
|
||||
"additional_special_tokens": [
|
||||
"<|user|>",
|
||||
"<|assistant|>",
|
||||
"<|system|>",
|
||||
"<|end|>",
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"tokenizer_class": "PreTrainedTokenizerFast",
|
||||
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}<|im_start|>system\n{{ message['content'] }}<|im_end|>\n{% elif message['role'] == 'user' %}<|im_start|>user\n{{ message['content'] }}<|im_end|>\n{% elif message['role'] == 'assistant' %}<|im_start|>assistant\n{{ message['content'] }}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
||||
}
|
||||
Reference in New Issue
Block a user